Stocks:Infochimps: StockPrice regression:: Stocks_BlueChips_2016
bdanalytics
Date: (Thu) Apr 21, 2016
Introduction:
Data: Source: Training:
https://d37djvu3ytnwxt.cloudfront.net/asset-v1:MITx+15.071x_3+1T2016+type@asset+block/IBMStock.csv https://d37djvu3ytnwxt.cloudfront.net/asset-v1:MITx+15.071x_3+1T2016+type@asset+block/GEStock.csv https://d37djvu3ytnwxt.cloudfront.net/asset-v1:MITx+15.071x_3+1T2016+type@asset+block/ProcterGambleStock.csv https://d37djvu3ytnwxt.cloudfront.net/asset-v1:MITx+15.071x_3+1T2016+type@asset+block/CocaColaStock.csv https://d37djvu3ytnwxt.cloudfront.net/asset-v1:MITx+15.071x_3+1T2016+type@asset+block/BoeingStock.csv
New:
Time period:
Synopsis:
Based on analysis utilizing <> techniques,
Summary of key steps & error improvement stats:
Prediction Accuracy Enhancement Options:
- transform.data chunk:
- derive features from multiple features
- manage.missing.data chunk:
- Not fill missing vars
- Fill missing numerics with a different algorithm
- Fill missing chars with data based on clusters
[](.png)
Potential next steps include:
- Organization:
- Categorize by chunk
- Priority criteria:
- Ease of change
- Impacts report
- Cleans innards
- Bug report
- all chunks:
- at chunk-end rm(!glb_)
- manage.missing.data chunk:
- cleaner way to manage re-splitting of training vs. new entity
- extract.features chunk:
- Add n-grams for glbFeatsText
- “RTextTools”, “tau”, “RWeka”, and “textcat” packages
- Add n-grams for glbFeatsText
- fit.models chunk:
- Classification: Plot AUC Curves for all models & highlight glbMdlSel
- Prediction accuracy scatter graph:
- Add tiles (raw vs. PCA)
- Use shiny for drop-down of “important” features
Use plot.ly for interactive plots ?
- Change .fit suffix of model metrics to .mdl if it’s data independent (e.g. AIC, Adj.R.Squared - is it truly data independent ?, etc.)
- create a custom model for rpart that has minbucket as a tuning parameter
varImp for randomForest crashes in caret version:6.0.41 -> submit bug report
- Probability handling for multinomials vs. desired binomial outcome
- ROCR currently supports only evaluation of binary classification tasks (version 1.0.7)
extensions toward multiclass classification are scheduled for the next release
- fit.all.training chunk:
- myplot_prediction_classification: displays ‘x’ instead of ‘+’ when there are no prediction errors
- Compare glb_sel_mdl vs. glb_fin_mdl:
- varImp
- Prediction differences (shd be minimal ?)
- Move glb_analytics_diag_plots to mydsutils.R: (+) Easier to debug (-) Too many glb vars used
- Add print(ggplot.petrinet(glb_analytics_pn) + coord_flip()) at the end of every major chunk
- Parameterize glb_analytics_pn
- Move glb_impute_missing_data to mydsutils.R: (-) Too many glb vars used; glb_<>_df reassigned
- Do non-glm methods handle interaction terms ?
- f-score computation for classifiers should be summation across outcomes (not just the desired one ?)
- Add accuracy computation to glb_dmy_mdl in predict.data.new chunk
- Why does splitting fit.data.training.all chunk into separate chunks add an overhead of ~30 secs ? It’s not rbind b/c other chunks have lower elapsed time. Is it the number of plots ?
- Incorporate code chunks in print_sessionInfo
- Test against
- projects in github.com/bdanalytics
- lectures in jhu-datascience track
Analysis:
rm(list = ls())
set.seed(12345)
options(stringsAsFactors = FALSE)
source("~/Dropbox/datascience/R/mycaret.R")
source("~/Dropbox/datascience/R/mydsutils.R")## Loading required package: caret## Loading required package: lattice## Loading required package: ggplot2source("~/Dropbox/datascience/R/mypetrinet.R")
source("~/Dropbox/datascience/R/myplclust.R")
source("~/Dropbox/datascience/R/myplot.R")
source("~/Dropbox/datascience/R/myscript.R")
source("~/Dropbox/datascience/R/mytm.R")
# Gather all package requirements here
suppressPackageStartupMessages(require(doMC))
glbCores <- 6 # of cores on machine - 2
registerDoMC(glbCores)
suppressPackageStartupMessages(require(caret))
require(plyr)## Loading required package: plyrrequire(dplyr)## Loading required package: dplyr##
## Attaching package: 'dplyr'## The following objects are masked from 'package:plyr':
##
## arrange, count, desc, failwith, id, mutate, rename, summarise,
## summarize## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionrequire(knitr)## Loading required package: knitrrequire(stringr)## Loading required package: stringr#source("dbgcaret.R")
#packageVersion("snow")
#require(sos); findFn("cosine", maxPages=2, sortby="MaxScore")
# Analysis control global variables
# Inputs
# url/name = "<PathPointer>"; if url specifies a zip file, name = "<filename>";
# or named collection of <PathPointer>s
# sep = choose from c(NULL, "\t")
glbObsTrnFile <- list(url = c(NULL
,IBM = "https://d37djvu3ytnwxt.cloudfront.net/asset-v1:MITx+15.071x_3+1T2016+type@asset+block/IBMStock.csv"
,GE = "https://d37djvu3ytnwxt.cloudfront.net/asset-v1:MITx+15.071x_3+1T2016+type@asset+block/GEStock.csv"
,PG = "https://d37djvu3ytnwxt.cloudfront.net/asset-v1:MITx+15.071x_3+1T2016+type@asset+block/ProcterGambleStock.csv"
,CC = "https://d37djvu3ytnwxt.cloudfront.net/asset-v1:MITx+15.071x_3+1T2016+type@asset+block/CocaColaStock.csv"
,BG = "https://d37djvu3ytnwxt.cloudfront.net/asset-v1:MITx+15.071x_3+1T2016+type@asset+block/BoeingStock.csv"
))
#, splitSpecs = list(method = "copy" # default when glbObsNewFile is NULL
# select from c("copy", NULL ???, "condition", "sample", )
# ,nRatio = 0.3 # > 0 && < 1 if method == "sample"
# ,seed = 123 # any integer or glbObsTrnPartitionSeed if method == "sample"
# ,condition = # or 'is.na(<var>)'; '<var> <condition_operator> <value>'
# )
# )
glbObsNewFile <- NULL # default OR list(url = "<obsNewFileName>")
glbObsDropCondition <- NULL # : default
# enclose in single-quotes b/c condition might include double qoutes
# use | & ; NOT || &&
# '<condition>'
# 'grepl("^First Draft Video:", glbObsAll$Headline)'
# 'is.na(glbObsAll[, glb_rsp_var_raw])'
# '(is.na(glbObsAll[, glb_rsp_var_raw]) & grepl("Train", glbObsAll[, glbFeatsId]))'
# 'is.na(strptime(glbObsAll[, "Date"], glbFeatsDateTime[["Date"]]["format"], tz = glbFeatsDateTime[["Date"]]["timezone"]))'
#nrow(do.call("subset",list(glbObsAll, parse(text=paste0("!(", glbObsDropCondition, ")")))))
glb_obs_repartition_train_condition <- NULL # : default
# "<condition>"
glb_max_fitobs <- NULL # or any integer
glbObsTrnPartitionSeed <- 123 # or any integer
glb_is_regression <- TRUE; glb_is_classification <- !glb_is_regression;
glb_is_binomial <- NULL # or TRUE or FALSE
glb_rsp_var_raw <- "StockPrice"
# for classification, the response variable has to be a factor
glb_rsp_var <- glb_rsp_var_raw # or "StockPrice.fctr"
# if the response factor is based on numbers/logicals e.g (0/1 OR TRUE/FALSE vs. "A"/"B"),
# or contains spaces (e.g. "Not in Labor Force")
# caret predict(..., type="prob") crashes
glb_map_rsp_raw_to_var <- NULL
# function(raw) {
# return(raw ^ 0.5)
# return(log(raw))
# return(log(1 + raw))
# return(log10(raw))
# return(exp(-raw / 2))
# ret_vals <- rep_len(NA, length(raw)); ret_vals[!is.na(raw)] <- ifelse(raw[!is.na(raw)] == 1, "Y", "N"); return(relevel(as.factor(ret_vals), ref="N"))
# as.factor(paste0("B", raw))
# as.factor(gsub(" ", "\\.", raw))
# }
#if glb_rsp_var_raw is numeric:
#print(summary(glbObsAll[, glb_rsp_var_raw]))
#glb_map_rsp_raw_to_var(tst <- c(NA, as.numeric(summary(glbObsAll[, glb_rsp_var_raw]))))
#if glb_rsp_var_raw is character:
#print(table(glbObsAll[, glb_rsp_var_raw], useNA = "ifany"))
#print(table(glb_map_rsp_raw_to_var(tst <- glbObsAll[, glb_rsp_var_raw]), useNA = "ifany"))
glb_map_rsp_var_to_raw <- NULL
# function(var) {
# return(var ^ 2.0)
# return(exp(var))
# return(10 ^ var)
# return(-log(var) * 2)
# as.numeric(var)
# levels(var)[as.numeric(var)]
# gsub("\\.", " ", levels(var)[as.numeric(var)])
# c("<=50K", " >50K")[as.numeric(var)]
# c(FALSE, TRUE)[as.numeric(var)]
# }
#print(table(glb_map_rsp_var_to_raw(glb_map_rsp_raw_to_var(tst)), useNA = "ifany"))
if ((glb_rsp_var != glb_rsp_var_raw) && is.null(glb_map_rsp_raw_to_var))
stop("glb_map_rsp_raw_to_var function expected")
# List info gathered for various columns
# <col_name>: <description>; <notes>
# Date: the date of the stock price, always given as the first of the month.
# StockPrice: the average stock price of the company in the given month.
# currently does not handle more than 1 column; consider concatenating multiple columns
# If glbFeatsId == NULL, ".rownames <- as.numeric(row.names())" is the default
glbFeatsId <- NULL # choose from c(NULL : default, "<id_feat>")
glbFeatsCategory <- ".inp" # choose from c(NULL : default, "<category_feat>")
# User-specified exclusions
glbFeatsExclude <- c(NULL
# Feats that shd be excluded due to known causation by prediction variable
# , "<feat1", "<feat2>"
# Feats that are factors with unique values (as % of nObs) > 49 (empirically derived)
# Feats that are linear combinations (alias in glm)
# Feature-engineering phase -> start by excluding all features except id & category & work each one in
, "Date.year.fctr"
)
if (glb_rsp_var_raw != glb_rsp_var)
glbFeatsExclude <- union(glbFeatsExclude, glb_rsp_var_raw)
glbFeatsInteractionOnly <- list()
#glbFeatsInteractionOnly[["<child_feat>"]] <- "<parent_feat>"
glbFeatsDrop <- c(NULL
# , "<feat1>", "<feat2>"
)
glb_map_vars <- NULL # or c("<var1>", "<var2>")
glb_map_urls <- list();
# glb_map_urls[["<var1>"]] <- "<var1.url>"
glb_assign_pairs_lst <- NULL;
# glb_assign_pairs_lst[["<var1>"]] <- list(from=c(NA),
# to=c("NA.my"))
glb_assign_vars <- names(glb_assign_pairs_lst)
# Derived features; Use this mechanism to cleanse data ??? Cons: Data duplication ???
glbFeatsDerive <- list();
# glbFeatsDerive[["<feat.my.sfx>"]] <- list(
# mapfn = function(<arg1>, <arg2>) { return(function(<arg1>, <arg2>)) }
# , args = c("<arg1>", "<arg2>"))
#myprint_df(data.frame(ImageId = mapfn(glbObsAll$.src, glbObsAll$.pos)))
#data.frame(ImageId = mapfn(glbObsAll$.src, glbObsAll$.pos))[7045:7055, ]
# character
# mapfn = function(Week) { return(substr(Week, 1, 10)) }
# mapfn = function(Name) { return(sapply(Name, function(thsName)
# str_sub(unlist(str_split(thsName, ","))[1], 1, 1))) }
# mapfn = function(descriptor) { return(plyr::revalue(descriptor, c(
# "ABANDONED BUILDING" = "OTHER",
# "**" = "**"
# ))) }
# mapfn = function(description) { mod_raw <- description;
# This is here because it does not work if it's in txt_map_filename
# mod_raw <- gsub(paste0(c("\n", "\211", "\235", "\317", "\333"), collapse = "|"), " ", mod_raw)
# Don't parse for "." because of ".com"; use customized gsub for that text
# mod_raw <- gsub("(\\w)(!|\\*|,|-|/)(\\w)", "\\1\\2 \\3", mod_raw);
# Some state acrnoyms need context for separation e.g.
# LA/L.A. could either be "Louisiana" or "LosAngeles"
# modRaw <- gsub("\\bL\\.A\\.( |,|')", "LosAngeles\\1", modRaw);
# OK/O.K. could either be "Oklahoma" or "Okay"
# modRaw <- gsub("\\bACA OK\\b", "ACA OKay", modRaw);
# modRaw <- gsub("\\bNow O\\.K\\.\\b", "Now OKay", modRaw);
# PR/P.R. could either be "PuertoRico" or "Public Relations"
# modRaw <- gsub("\\bP\\.R\\. Campaign", "PublicRelations Campaign", modRaw);
# VA/V.A. could either be "Virginia" or "VeteransAdministration"
# modRaw <- gsub("\\bthe V\\.A\\.\\:", "the VeteranAffairs:", modRaw);
#
# Custom mods
# return(mod_raw) }
# numeric
# Create feature based on record position/id in data
glbFeatsDerive[[".pos"]] <- list(
mapfn = function(.rnorm) { return(1:length(.rnorm)) }
, args = c(".rnorm"))
glbFeatsDerive[[".pos.y"]] <- list(
mapfn = function(.rnorm) { return(1:length(.rnorm)) }
, args = c(".rnorm"))
# Add logs of numerics that are not distributed normally
# Derive & keep multiple transformations of the same feature, if normality is hard to achieve with just one transformation
# Right skew: logp1; sqrt; ^ 1/3; logp1(logp1); log10; exp(-<feat>/constant)
# glbFeatsDerive[["WordCount.log1p"]] <- list(
# mapfn = function(WordCount) { return(log1p(WordCount)) }
# , args = c("WordCount"))
# glbFeatsDerive[["WordCount.root2"]] <- list(
# mapfn = function(WordCount) { return(WordCount ^ (1/2)) }
# , args = c("WordCount"))
# glbFeatsDerive[["WordCount.nexp"]] <- list(
# mapfn = function(WordCount) { return(exp(-WordCount)) }
# , args = c("WordCount"))
#print(summary(glbObsAll$WordCount))
#print(summary(mapfn(glbObsAll$WordCount)))
# If imputation shd be skipped for this feature
# glbFeatsDerive[["District.fctr"]] <- list(
# mapfn = function(District) {
# raw <- District;
# ret_vals <- rep_len("NA", length(raw));
# ret_vals[!is.na(raw)] <- sapply(raw[!is.na(raw)], function(elm)
# ifelse(elm < 10, "1-9",
# ifelse(elm < 20, "10-19", "20+")));
# return(relevel(as.factor(ret_vals), ref = "NA"))
# }
# , args = c("District"))
# If imputation of missing data is not working ...
# glbFeatsDerive[["FertilityRate.nonNA"]] <- list(
# mapfn = function(FertilityRate, Region) {
# RegionMdn <- tapply(FertilityRate, Region, FUN = median, na.rm = TRUE)
#
# retVal <- FertilityRate
# retVal[is.na(FertilityRate)] <- RegionMdn[Region[is.na(FertilityRate)]]
# return(retVal)
# }
# , args = c("FertilityRate", "Region"))
# mapfn = function(HOSPI.COST) { return(cut(HOSPI.COST, 5, breaks = c(0, 100000, 200000, 300000, 900000), labels = NULL)) }
# mapfn = function(Rasmussen) { return(ifelse(sign(Rasmussen) >= 0, 1, 0)) }
# mapfn = function(startprice) { return(startprice ^ (1/2)) }
# mapfn = function(startprice) { return(log(startprice)) }
# mapfn = function(startprice) { return(exp(-startprice / 20)) }
# mapfn = function(startprice) { return(scale(log(startprice))) }
# mapfn = function(startprice) { return(sign(sprice.predict.diff) * (abs(sprice.predict.diff) ^ (1/10))) }
# factor
# mapfn = function(PropR) { return(as.factor(ifelse(PropR >= 0.5, "Y", "N"))) }
# mapfn = function(productline, description) { as.factor(gsub(" ", "", productline)) }
# mapfn = function(purpose) { return(relevel(as.factor(purpose), ref="all_other")) }
# mapfn = function(raw) { tfr_raw <- as.character(cut(raw, 5));
# tfr_raw[is.na(tfr_raw)] <- "NA.my";
# return(as.factor(tfr_raw)) }
# mapfn = function(startprice.log10) { return(cut(startprice.log10, 3)) }
# mapfn = function(startprice.log10) { return(cut(sprice.predict.diff, c(-1000, -100, -10, -1, 0, 1, 10, 100, 1000))) }
# , args = c("<arg1>"))
# multiple args
# mapfn = function(id, date) { return(paste(as.character(id), as.character(date), sep = "#")) }
# mapfn = function(PTS, oppPTS) { return(PTS - oppPTS) }
# mapfn = function(startprice.log10.predict, startprice) {
# return(spdiff <- (10 ^ startprice.log10.predict) - startprice) }
# mapfn = function(productline, description) { as.factor(
# paste(gsub(" ", "", productline), as.numeric(nchar(description) > 0), sep = "*")) }
# mapfn = function(.src, .pos) {
# return(paste(.src, sprintf("%04d",
# ifelse(.src == "Train", .pos, .pos - 7049)
# ), sep = "#")) }
# # If glbObsAll is not sorted in the desired manner
# mapfn=function(Week) { return(coredata(lag(zoo(orderBy(~Week, glbObsAll)$ILI), -2, na.pad=TRUE))) }
# mapfn=function(ILI) { return(coredata(lag(zoo(ILI), -2, na.pad=TRUE))) }
# mapfn=function(ILI.2.lag) { return(log(ILI.2.lag)) }
# glbFeatsDerive[["<var1>"]] <- glbFeatsDerive[["<var2>"]]
glb_derive_vars <- names(glbFeatsDerive)
# tst <- "descr.my"; args_lst <- NULL; for (arg in glbFeatsDerive[[tst]]$args) args_lst[[arg]] <- glbObsAll[, arg]; print(head(args_lst[[arg]])); print(head(drv_vals <- do.call(glbFeatsDerive[[tst]]$mapfn, args_lst)));
# print(which_ix <- which(args_lst[[arg]] == 0.75)); print(drv_vals[which_ix]);
glbFeatsDateTime <- list()
# Use OlsonNames() to enumerate supported time zones
# glbFeatsDateTime[["<DateTimeFeat>"]] <-
# c(format = "%Y-%m-%d %H:%M:%S", timezone = "US/Eastern", impute.na = TRUE,
# last.ctg = FALSE, poly.ctg = FALSE)
glbFeatsDateTime[["Date"]] <-
c(format = "%m/%e/%y", timezone = "US/Eastern", impute.na = TRUE,
last.ctg = FALSE, poly.ctg = FALSE)
glbFeatsPrice <- NULL # or c("<price_var>")
glbFeatsImage <- list() #list(<imageFeat> = list(patchSize = 10)) # if patchSize not specified, no patch computation
glbFeatsText <- list()
Sys.setlocale("LC_ALL", "C") # For english## [1] "C/C/C/C/C/en_US.UTF-8"#glbFeatsText[["<TextFeature>"]] <- list(NULL,
# ,names = myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL,
# <comma-separated-screened-names>
# ))))
# ,rareWords = myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL,
# <comma-separated-nonSCOWL-words>
# ))))
#)
# Text Processing Step: custom modifications not present in txt_munge -> use glbFeatsDerive
# Text Processing Step: universal modifications
glb_txt_munge_filenames_pfx <- "<projectId>_mytxt_"
# Text Processing Step: tolower
# Text Processing Step: myreplacePunctuation
# Text Processing Step: removeWords
glb_txt_stop_words <- list()
# Remember to use unstemmed words
if (length(glbFeatsText) > 0) {
require(tm)
require(stringr)
glb_txt_stop_words[["<txt_var>"]] <- sort(myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL
# Remove any words from stopwords
# , setdiff(myreplacePunctuation(stopwords("english")), c("<keep_wrd1>", <keep_wrd2>"))
# Remove salutations
,"mr","mrs","dr","Rev"
# Remove misc
#,"th" # Happy [[:digit::]]+th birthday
# Remove terms present in Trn only or New only; search for "Partition post-stem"
# ,<comma-separated-terms>
# cor.y.train == NA
# ,unlist(strsplit(paste(c(NULL
# ,"<comma-separated-terms>"
# ), collapse=",")
# freq == 1; keep c("<comma-separated-terms-to-keep>")
# ,<comma-separated-terms>
# chisq.pval high (e.g. == 1); keep c("<comma-separated-terms-to-keep>")
# ,<comma-separated-terms>
# nzv.freqRatio high (e.g. >= glbFeatsNzvFreqMax); keep c("<comma-separated-terms-to-keep>")
# ,<comma-separated-terms>
)))))
}
#orderBy(~term, glb_post_stem_words_terms_df_lst[[txtFeat]][grep("^man", glb_post_stem_words_terms_df_lst[[txtFeat]]$term), ])
#glbObsAll[glb_post_stem_words_terms_mtrx_lst[[txtFeat]][, 4866] > 0, c(glb_rsp_var, txtFeat)]
# To identify terms with a specific freq
#paste0(sort(subset(glb_post_stop_words_terms_df_lst[[txtFeat]], freq == 1)$term), collapse = ",")
#paste0(sort(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], freq <= 2)$term), collapse = ",")
#subset(glb_post_stem_words_terms_df_lst[[txtFeat]], term %in% c("zinger"))
# To identify terms with a specific freq &
# are not stemmed together later OR is value of color.fctr (e.g. gold)
#paste0(sort(subset(glb_post_stop_words_terms_df_lst[[txtFeat]], (freq == 1) & !(term %in% c("blacked","blemish","blocked","blocks","buying","cables","careful","carefully","changed","changing","chargers","cleanly","cleared","connect","connects","connected","contains","cosmetics","default","defaulting","defective","definitely","describe","described","devices","displays","drop","drops","engravement","excellant","excellently","feels","fix","flawlessly","frame","framing","gentle","gold","guarantee","guarantees","handled","handling","having","install","iphone","iphones","keeped","keeps","known","lights","line","lining","liquid","liquidation","looking","lots","manuals","manufacture","minis","most","mostly","network","networks","noted","opening","operated","performance","performs","person","personalized","photograph","physically","placed","places","powering","pre","previously","products","protection","purchasing","returned","rotate","rotation","running","sales","second","seconds","shipped","shuts","sides","skin","skinned","sticker","storing","thats","theres","touching","unusable","update","updates","upgrade","weeks","wrapped","verified","verify") ))$term), collapse = ",")
#print(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], (freq <= 2)))
#glbObsAll[which(terms_mtrx[, 229] > 0), glbFeatsText]
# To identify terms with cor.y == NA
#orderBy(~-freq+term, subset(glb_post_stop_words_terms_df_lst[[txtFeat]], is.na(cor.y)))
#paste(sort(subset(glb_post_stop_words_terms_df_lst[[txtFeat]], is.na(cor.y))[, "term"]), collapse=",")
#orderBy(~-freq+term, subset(glb_post_stem_words_terms_df_lst[[txtFeat]], is.na(cor.y)))
# To identify terms with low cor.y.abs
#head(orderBy(~cor.y.abs+freq+term, subset(glb_post_stem_words_terms_df_lst[[txtFeat]], !is.na(cor.y))), 5)
# To identify terms with high chisq.pval
#subset(glb_post_stem_words_terms_df_lst[[txtFeat]], chisq.pval > 0.99)
#paste0(sort(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], (chisq.pval > 0.99) & (freq <= 10))$term), collapse=",")
#paste0(sort(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], (chisq.pval > 0.9))$term), collapse=",")
#head(orderBy(~-chisq.pval+freq+term, glb_post_stem_words_terms_df_lst[[txtFeat]]), 5)
#glbObsAll[glb_post_stem_words_terms_mtrx_lst[[txtFeat]][, 68] > 0, glbFeatsText]
#orderBy(~term, glb_post_stem_words_terms_df_lst[[txtFeat]][grep("^m", glb_post_stem_words_terms_df_lst[[txtFeat]]$term), ])
# To identify terms with high nzv.freqRatio
#summary(glb_post_stem_words_terms_df_lst[[txtFeat]]$nzv.freqRatio)
#paste0(sort(setdiff(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], (nzv.freqRatio >= glbFeatsNzvFreqMax) & (freq < 10) & (chisq.pval >= 0.05))$term, c( "128gb","3g","4g","gold","ipad1","ipad3","ipad4","ipadair2","ipadmini2","manufactur","spacegray","sprint","tmobil","verizon","wifion"))), collapse=",")
# To identify obs with a txt term
#tail(orderBy(~-freq+term, glb_post_stop_words_terms_df_lst[[txtFeat]]), 20)
#mydspObs(list(descr.my.contains="non"), cols=c("color", "carrier", "cellular", "storage"))
#grep("ever", dimnames(terms_stop_mtrx)$Terms)
#which(terms_stop_mtrx[, grep("ipad", dimnames(terms_stop_mtrx)$Terms)] > 0)
#glbObsAll[which(terms_stop_mtrx[, grep("16", dimnames(terms_stop_mtrx)$Terms)[1]] > 0), c(glbFeatsCategory, "storage", txtFeat)]
# Text Processing Step: screen for names # Move to glbFeatsText specs section in order of text processing steps
# glbFeatsText[["<txtFeat>"]]$names <- myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL
# # Person names for names screening
# ,<comma-separated-list>
#
# # Company names
# ,<comma-separated-list>
#
# # Product names
# ,<comma-separated-list>
# ))))
# glbFeatsText[["<txtFeat>"]]$rareWords <- myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL
# # Words not in SCOWL db
# ,<comma-separated-list>
# ))))
# To identify char vectors post glbFeatsTextMap
#grep("six(.*)hour", glb_txt_chr_lst[[txtFeat]], ignore.case = TRUE, value = TRUE)
#grep("[S|s]ix(.*)[H|h]our", glb_txt_chr_lst[[txtFeat]], value = TRUE)
# To identify whether terms shd be synonyms
#orderBy(~term, glb_post_stop_words_terms_df_lst[[txtFeat]][grep("^moder", glb_post_stop_words_terms_df_lst[[txtFeat]]$term), ])
# term_row_df <- glb_post_stop_words_terms_df_lst[[txtFeat]][grep("^came$", glb_post_stop_words_terms_df_lst[[txtFeat]]$term), ]
#
# cor(glb_post_stop_words_terms_mtrx_lst[[txtFeat]][glbObsAll$.lcn == "Fit", term_row_df$pos], glbObsTrn[, glb_rsp_var], use="pairwise.complete.obs")
# To identify which stopped words are "close" to a txt term
#sort(cluster_vars)
# Text Processing Step: stemDocument
# To identify stemmed txt terms
#glb_post_stop_words_terms_df_lst[[txtFeat]][grep("^la$", glb_post_stop_words_terms_df_lst[[txtFeat]]$term), ]
#orderBy(~term, glb_post_stem_words_terms_df_lst[[txtFeat]][grep("^con", glb_post_stem_words_terms_df_lst[[txtFeat]]$term), ])
#glbObsAll[which(terms_stem_mtrx[, grep("use", dimnames(terms_stem_mtrx)$Terms)[[1]]] > 0), c(glbFeatsId, "productline", txtFeat)]
#glbObsAll[which(TfIdf_stem_mtrx[, 191] > 0), c(glbFeatsId, glbFeatsCategory, txtFeat)]
#glbObsAll[which(glb_post_stop_words_terms_mtrx_lst[[txtFeat]][, 6165] > 0), c(glbFeatsId, glbFeatsCategory, txtFeat)]
#which(glbObsAll$UniqueID %in% c(11915, 11926, 12198))
# Text Processing Step: mycombineSynonyms
# To identify which terms are associated with not -> combine "could not" & "couldn't"
#findAssocs(glb_full_DTM_lst[[txtFeat]], "not", 0.05)
# To identify which synonyms should be combined
#orderBy(~term, glb_post_stem_words_terms_df_lst[[txtFeat]][grep("^c", glb_post_stem_words_terms_df_lst[[txtFeat]]$term), ])
chk_comb_cor <- function(syn_lst) {
# cor(terms_stem_mtrx[glbObsAll$.src == "Train", grep("^(damag|dent|ding)$", dimnames(terms_stem_mtrx)[[2]])], glbObsTrn[, glb_rsp_var], use="pairwise.complete.obs")
print(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], term %in% syn_lst$syns))
print(subset(get_corpus_terms(tm_map(glbFeatsTextCorpus[[txtFeat]], mycombineSynonyms, list(syn_lst), lazy=FALSE)), term == syn_lst$word))
# cor(terms_stop_mtrx[glbObsAll$.src == "Train", grep("^(damage|dent|ding)$", dimnames(terms_stop_mtrx)[[2]])], glbObsTrn[, glb_rsp_var], use="pairwise.complete.obs")
# cor(rowSums(terms_stop_mtrx[glbObsAll$.src == "Train", grep("^(damage|dent|ding)$", dimnames(terms_stop_mtrx)[[2]])]), glbObsTrn[, glb_rsp_var], use="pairwise.complete.obs")
}
#chk_comb_cor(syn_lst=list(word="cabl", syns=c("cabl", "cord")))
#chk_comb_cor(syn_lst=list(word="damag", syns=c("damag", "dent", "ding")))
#chk_comb_cor(syn_lst=list(word="dent", syns=c("dent", "ding")))
#chk_comb_cor(syn_lst=list(word="use", syns=c("use", "usag")))
glbFeatsTextSynonyms <- list()
# list parsed to collect glbFeatsText[[<txtFeat>]]$vldTerms
# glbFeatsTextSynonyms[["Hdln.my"]] <- list(NULL
# # people in places
# , list(word = "australia", syns = c("australia", "australian"))
# , list(word = "italy", syns = c("italy", "Italian"))
# , list(word = "newyork", syns = c("newyork", "newyorker"))
# , list(word = "Pakistan", syns = c("Pakistan", "Pakistani"))
# , list(word = "peru", syns = c("peru", "peruvian"))
# , list(word = "qatar", syns = c("qatar", "qatari"))
# , list(word = "scotland", syns = c("scotland", "scotish"))
# , list(word = "Shanghai", syns = c("Shanghai", "Shanzhai"))
# , list(word = "venezuela", syns = c("venezuela", "venezuelan"))
#
# # companies - needs to be data dependent
# # - e.g. ensure BNP in this experiment/feat always refers to BNPParibas
#
# # general synonyms
# , list(word = "Create", syns = c("Create","Creator"))
# , list(word = "cute", syns = c("cute","cutest"))
# , list(word = "Disappear", syns = c("Disappear","Fadeout"))
# , list(word = "teach", syns = c("teach", "taught"))
# , list(word = "theater", syns = c("theater", "theatre", "theatres"))
# , list(word = "understand", syns = c("understand", "understood"))
# , list(word = "weak", syns = c("weak", "weaken", "weaker", "weakest"))
# , list(word = "wealth", syns = c("wealth", "wealthi"))
#
# # custom synonyms (phrases)
#
# # custom synonyms (names)
# )
#glbFeatsTextSynonyms[["<txtFeat>"]] <- list(NULL
# , list(word="<stem1>", syns=c("<stem1>", "<stem1_2>"))
# )
for (txtFeat in names(glbFeatsTextSynonyms))
for (entryIx in 1:length(glbFeatsTextSynonyms[[txtFeat]])) {
glbFeatsTextSynonyms[[txtFeat]][[entryIx]]$word <-
str_to_lower(glbFeatsTextSynonyms[[txtFeat]][[entryIx]]$word)
glbFeatsTextSynonyms[[txtFeat]][[entryIx]]$syns <-
str_to_lower(glbFeatsTextSynonyms[[txtFeat]][[entryIx]]$syns)
}
glbFeatsTextSeed <- 181
# tm options include: check tm::weightSMART
glb_txt_terms_control <- list( # Gather model performance & run-time stats
# weighting = function(x) weightSMART(x, spec = "nnn")
# weighting = function(x) weightSMART(x, spec = "lnn")
# weighting = function(x) weightSMART(x, spec = "ann")
# weighting = function(x) weightSMART(x, spec = "bnn")
# weighting = function(x) weightSMART(x, spec = "Lnn")
#
weighting = function(x) weightSMART(x, spec = "ltn") # default
# weighting = function(x) weightSMART(x, spec = "lpn")
#
# weighting = function(x) weightSMART(x, spec = "ltc")
#
# weighting = weightBin
# weighting = weightTf
# weighting = weightTfIdf # : default
# termFreq selection criteria across obs: tm default: list(global=c(1, Inf))
, bounds = list(global = c(1, Inf))
# wordLengths selection criteria: tm default: c(3, Inf)
, wordLengths = c(1, Inf)
)
glb_txt_cor_var <- glb_rsp_var # : default # or c(<feat>)
# select one from c("union.top.val.cor", "top.cor", "top.val", default: "top.chisq", "sparse")
glbFeatsTextFilter <- "top.chisq"
glbFeatsTextTermsMax <- rep(10, length(glbFeatsText)) # :default
names(glbFeatsTextTermsMax) <- names(glbFeatsText)
# Text Processing Step: extractAssoc
glbFeatsTextAssocCor <- rep(1, length(glbFeatsText)) # :default
names(glbFeatsTextAssocCor) <- names(glbFeatsText)
# Remember to use stemmed terms
glb_important_terms <- list()
# Text Processing Step: extractPatterns (ngrams)
glbFeatsTextPatterns <- list()
#glbFeatsTextPatterns[[<txtFeat>>]] <- list()
#glbFeatsTextPatterns[[<txtFeat>>]] <- c(metropolitan.diary.colon = "Metropolitan Diary:")
# Have to set it even if it is not used
# Properties:
# numrows(glb_feats_df) << numrows(glbObsFit
# Select terms that appear in at least 0.2 * O(FP/FN(glbObsOOB)) ???
# numrows(glbObsOOB) = 1.1 * numrows(glbObsNew) ???
glb_sprs_thresholds <- NULL # or c(<txtFeat1> = 0.988, <txtFeat2> = 0.970, <txtFeat3> = 0.970)
glbFctrMaxUniqVals <- 20 # default: 20
glb_impute_na_data <- FALSE # or TRUE
glb_mice_complete.seed <- 144 # or any integer
glb_cluster <- FALSE # : default or TRUE
glb_cluster.seed <- 189 # or any integer
glb_cluster_entropy_var <- NULL # c(glb_rsp_var, as.factor(cut(glb_rsp_var, 3)), default: NULL)
glbFeatsTextClusterVarsExclude <- FALSE # default FALSE
glb_interaction_only_feats <- NULL # : default or c(<parent_feat> = "<child_feat>")
glbFeatsNzvFreqMax <- 19 # 19 : caret default
glbFeatsNzvUniqMin <- 10 # 10 : caret default
glbRFESizes <- list()
#glbRFESizes[["mdlFamily"]] <- c(4, 8, 16, 32, 64, 67, 68, 69) # Accuracy@69/70 = 0.8258
glbObsFitOutliers <- list()
# If outliers.n >= 10; consider concatenation of interaction vars
# glbObsFitOutliers[["<mdlFamily>"]] <- c(NULL
# is.na(.rstudent)
# max(.rstudent)
# is.na(.dffits)
# .hatvalues >= 0.99
# -38,167,642 < minmax(.rstudent) < 49,649,823
# , <comma-separated-<glbFeatsId>>
# )
glbObsTrnOutliers <- list()
glbObsTrnOutliers[["Final"]] <- union(glbObsFitOutliers[["All.X"]],
c(NULL
))
# influence.measures: car::outlier; rstudent; dffits; hatvalues; dfbeta; dfbetas
#mdlId <- "All.X##rcv#glm"; obs_df <- fitobs_df
#mdlId <- "RFE.X.glm"; obs_df <- fitobs_df
#mdlId <- "Final.glm"; obs_df <- trnobs_df
#mdlId <- "CSM2.X.glm"; obs_df <- fitobs_df
#print(outliers <- car::outlierTest(glb_models_lst[[mdlId]]$finalModel))
#mdlIdFamily <- paste0(head(unlist(str_split(mdlId, "\\.")), -1), collapse="."); obs_df <- dplyr::filter_(obs_df, interp(~(!(var %in% glbObsFitOutliers[[mdlIdFamily]])), var = as.name(glbFeatsId))); model_diags_df <- cbind(obs_df, data.frame(.rstudent=stats::rstudent(glb_models_lst[[mdlId]]$finalModel)), data.frame(.dffits=stats::dffits(glb_models_lst[[mdlId]]$finalModel)), data.frame(.hatvalues=stats::hatvalues(glb_models_lst[[mdlId]]$finalModel)));print(summary(model_diags_df[, c(".rstudent",".dffits",".hatvalues")])); table(cut(model_diags_df$.hatvalues, breaks=c(0.00, 0.98, 0.99, 1.00)))
#print(subset(model_diags_df, is.na(.rstudent))[, glbFeatsId])
#print(model_diags_df[which.max(model_diags_df$.rstudent), ])
#print(subset(model_diags_df, is.na(.dffits))[, glbFeatsId])
#print(model_diags_df[which.min(model_diags_df$.dffits), ])
#print(subset(model_diags_df, .hatvalues > 0.99)[, glbFeatsId])
#dffits_df <- merge(dffits_df, outliers_df, by="row.names", all.x=TRUE); row.names(dffits_df) <- dffits_df$Row.names; dffits_df <- subset(dffits_df, select=-Row.names)
#dffits_df <- merge(dffits_df, glbObsFit, by="row.names", all.x=TRUE); row.names(dffits_df) <- dffits_df$Row.names; dffits_df <- subset(dffits_df, select=-Row.names)
#subset(dffits_df, !is.na(.Bonf.p))
#mdlId <- "CSM.X.glm"; vars <- myextract_actual_feats(row.names(orderBy(reformulate(c("-", paste0(mdlId, ".imp"))), myget_feats_imp(glb_models_lst[[mdlId]]))));
#model_diags_df <- glb_get_predictions(model_diags_df, mdlId, glb_rsp_var)
#obs_ix <- row.names(model_diags_df) %in% names(outliers$rstudent)[1]
#obs_ix <- which(is.na(model_diags_df$.rstudent))
#obs_ix <- which(is.na(model_diags_df$.dffits))
#myplot_parcoord(obs_df=model_diags_df[, c(glbFeatsId, glbFeatsCategory, ".rstudent", ".dffits", ".hatvalues", glb_rsp_var, paste0(glb_rsp_var, mdlId), vars[1:min(20, length(vars))])], obs_ix=obs_ix, id_var=glbFeatsId, category_var=glbFeatsCategory)
#model_diags_df[row.names(model_diags_df) %in% names(outliers$rstudent)[c(1:2)], ]
#ctgry_diags_df <- model_diags_df[model_diags_df[, glbFeatsCategory] %in% c("Unknown#0"), ]
#myplot_parcoord(obs_df=ctgry_diags_df[, c(glbFeatsId, glbFeatsCategory, ".rstudent", ".dffits", ".hatvalues", glb_rsp_var, "startprice.log10.predict.RFE.X.glmnet", indepVar[1:20])], obs_ix=row.names(ctgry_diags_df) %in% names(outliers$rstudent)[1], id_var=glbFeatsId, category_var=glbFeatsCategory)
#table(glbObsFit[model_diags_df[, glbFeatsCategory] %in% c("iPad1#1"), "startprice.log10.cut.fctr"])
#glbObsFit[model_diags_df[, glbFeatsCategory] %in% c("iPad1#1"), c(glbFeatsId, "startprice")]
# No outliers & .dffits == NaN
#myplot_parcoord(obs_df=model_diags_df[, c(glbFeatsId, glbFeatsCategory, glb_rsp_var, "startprice.log10.predict.RFE.X.glmnet", indepVar[1:10])], obs_ix=seq(1:nrow(model_diags_df))[is.na(model_diags_df$.dffits)], id_var=glbFeatsId, category_var=glbFeatsCategory)
# Modify mdlId to (build & extract) "<FamilyId>#<Fit|Trn>#<caretMethod>#<preProc1.preProc2>#<samplingMethod>"
glb_models_lst <- list(); glb_models_df <- data.frame()
# Regression
if (glb_is_regression) {
glbMdlMethods <- c(NULL
# deterministic
#, "lm", # same as glm
, "glm", "bayesglm", "glmnet"
, "rpart"
# non-deterministic
, "gbm", "rf"
# Unknown
, "nnet" , "avNNet" # runs 25 models per cv sample for tunelength=5
, "svmLinear", "svmLinear2"
, "svmPoly" # runs 75 models per cv sample for tunelength=5
, "svmRadial"
, "earth"
, "bagEarth" # Takes a long time
)
} else
# Classification - Add ada (auto feature selection)
if (glb_is_binomial)
glbMdlMethods <- c(NULL
# deterministic
, "bagEarth" # Takes a long time
, "glm", "bayesglm", "glmnet"
, "nnet"
, "rpart"
# non-deterministic
, "gbm"
, "avNNet" # runs 25 models per cv sample for tunelength=5
, "rf"
# Unknown
, "lda", "lda2"
# svm models crash when predict is called -> internal to kernlab it should call predict without .outcome
, "svmLinear", "svmLinear2"
, "svmPoly" # runs 75 models per cv sample for tunelength=5
, "svmRadial"
, "earth"
) else
glbMdlMethods <- c(NULL
# deterministic
,"glmnet"
# non-deterministic
,"rf"
# Unknown
,"gbm","rpart"
)
glbMdlFamilies <- list(); glb_mdl_feats_lst <- list()
# family: Choose from c("RFE.X", "CSM.X", "All.X", "Best.Interact")
# methods: Choose from c(NULL, <method>, glbMdlMethods)
#glbMdlFamilies[["RFE.X"]] <- c("glmnet", "glm") # non-NULL vector is mandatory
glbMdlFamilies[["All.X"]] <- c("glmnet", "glm") # non-NULL vector is mandatory
#glbMdlFamilies[["Best.Interact"]] <- "glmnet" # non-NULL vector is mandatory
# Check if interaction features make RFE better
# glbMdlFamilies[["CSM.X"]] <- setdiff(glbMdlMethods, c("lda", "lda2")) # crashing due to category:.clusterid ??? #c("glmnet", "glm") # non-NULL list is mandatory
# glb_mdl_feats_lst[["CSM.X"]] <- c(NULL
# , <comma-separated-features-vector>
# )
# dAFeats.CSM.X %<d-% c(NULL
# # Interaction feats up to varImp(RFE.X.glmnet) >= 50
# , <comma-separated-features-vector>
# , setdiff(myextract_actual_feats(predictors(rfe_fit_results)), c(NULL
# , <comma-separated-features-vector>
# ))
# )
# glb_mdl_feats_lst[["CSM.X"]] <- "%<d-% dAFeats.CSM.X"
glbMdlFamilies[["Final"]] <- c(NULL) # NULL vector acceptable # c("glmnet", "glm")
glbMdlAllowParallel <- list()
#glbMdlAllowParallel[["<mdlId>"]] <- FALSE
glbMdlAllowParallel[["All.X##rcv#glm"]] <- FALSE
# Check if tuning parameters make fit better; make it mdlFamily customizable ?
glbMdlTuneParams <- data.frame()
# When glmnet crashes at model$grid with error: ???
glmnetTuneParams <- rbind(data.frame()
,data.frame(parameter = "alpha", vals = "0.100 0.325 0.550 0.775 1.000")
,data.frame(parameter = "lambda", vals = "9.342e-02")
)
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams,
# cbind(data.frame(mdlId = "<mdlId>"),
# glmnetTuneParams))
#avNNet
# size=[1] 3 5 7 9; decay=[0] 1e-04 0.001 0.01 0.1; bag=[FALSE]; RMSE=1.3300906
#bagEarth
# degree=1 [2] 3; nprune=64 128 256 512 [1024]; RMSE=0.6486663 (up)
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "bagEarth", parameter = "nprune", vals = "256")
# ,data.frame(method = "bagEarth", parameter = "degree", vals = "2")
# ))
#earth
# degree=[1]; nprune=2 [9] 17 25 33; RMSE=0.1334478
#gbm
# shrinkage=0.05 [0.10] 0.15 0.20 0.25; n.trees=100 150 200 [250] 300; interaction.depth=[1] 2 3 4 5; n.minobsinnode=[10]; RMSE=0.2008313
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "gbm", parameter = "shrinkage", min = 0.05, max = 0.25, by = 0.05)
# ,data.frame(method = "gbm", parameter = "n.trees", min = 100, max = 300, by = 50)
# ,data.frame(method = "gbm", parameter = "interaction.depth", min = 1, max = 5, by = 1)
# ,data.frame(method = "gbm", parameter = "n.minobsinnode", min = 10, max = 10, by = 10)
# #seq(from=0.05, to=0.25, by=0.05)
# ))
#glmnet
# alpha=0.100 [0.325] 0.550 0.775 1.000; lambda=0.0005232693 0.0024288010 0.0112734954 [0.0523269304] 0.2428800957; RMSE=0.6164891
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "glmnet", parameter = "alpha", vals = "0.550 0.775 0.8875 0.94375 1.000")
# ,data.frame(method = "glmnet", parameter = "lambda", vals = "9.858855e-05 0.0001971771 0.0009152152 0.0042480525 0.0197177130")
# ))
#nnet
# size=3 5 [7] 9 11; decay=0.0001 0.001 0.01 [0.1] 0.2; RMSE=0.9287422
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "nnet", parameter = "size", vals = "3 5 7 9 11")
# ,data.frame(method = "nnet", parameter = "decay", vals = "0.0001 0.0010 0.0100 0.1000 0.2000")
# ))
#rf # Don't bother; results are not deterministic
# mtry=2 35 68 [101] 134; RMSE=0.1339974
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "rf", parameter = "mtry", vals = "2 5 9 13 17")
# ))
#rpart
# cp=0.020 [0.025] 0.030 0.035 0.040; RMSE=0.1770237
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "rpart", parameter = "cp", vals = "0.004347826 0.008695652 0.017391304 0.021739130 0.034782609")
# ))
#svmLinear
# C=0.01 0.05 [0.10] 0.50 1.00 2.00 3.00 4.00; RMSE=0.1271318; 0.1296718
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "svmLinear", parameter = "C", vals = "0.01 0.05 0.1 0.5 1")
# ))
#svmLinear2
# cost=0.0625 0.1250 [0.25] 0.50 1.00; RMSE=0.1276354
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "svmLinear2", parameter = "cost", vals = "0.0625 0.125 0.25 0.5 1")
# ))
#svmPoly
# degree=[1] 2 3 4 5; scale=0.01 0.05 [0.1] 0.5 1; C=0.50 1.00 [2.00] 3.00 4.00; RMSE=0.1276130
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method="svmPoly", parameter="degree", min=1, max=5, by=1) #seq(1, 5, 1)
# ,data.frame(method="svmPoly", parameter="scale", vals="0.01, 0.05, 0.1, 0.5, 1")
# ,data.frame(method="svmPoly", parameter="C", vals="0.50, 1.00, 2.00, 3.00, 4.00")
# ))
#svmRadial
# sigma=[0.08674323]; C=0.25 0.50 1.00 [2.00] 4.00; RMSE=0.1614957
#glb2Sav(); all.equal(sav_models_df, glb_models_df)
glb_preproc_methods <- NULL
# c("YeoJohnson", "center.scale", "range", "pca", "ica", "spatialSign")
# Baseline prediction model feature(s)
glb_Baseline_mdl_var <- NULL # or c("<feat>")
glbMdlMetric_terms <- NULL # or matrix(c(
# 0,1,2,3,4,
# 2,0,1,2,3,
# 4,2,0,1,2,
# 6,4,2,0,1,
# 8,6,4,2,0
# ), byrow=TRUE, nrow=5)
glbMdlMetricSummary <- NULL # or "<metric_name>"
glbMdlMetricMaximize <- NULL # or FALSE (TRUE is not the default for both classification & regression)
glbMdlMetricSummaryFn <- NULL # or function(data, lev=NULL, model=NULL) {
# confusion_mtrx <- t(as.matrix(confusionMatrix(data$pred, data$obs)))
# #print(confusion_mtrx)
# #print(confusion_mtrx * glbMdlMetric_terms)
# metric <- sum(confusion_mtrx * glbMdlMetric_terms) / nrow(data)
# names(metric) <- glbMdlMetricSummary
# return(metric)
# }
glbMdlCheckRcv <- FALSE # Turn it on when needed; otherwise takes long time
glb_rcv_n_folds <- 3 # or NULL
glb_rcv_n_repeats <- 3 # or NULL
glb_clf_proba_threshold <- NULL # 0.5
# Model selection criteria
if (glb_is_regression)
glbMdlMetricsEval <- c("min.RMSE.OOB", "max.R.sq.OOB", "max.Adj.R.sq.fit", "min.RMSE.fit")
#glbMdlMetricsEval <- c("min.RMSE.fit", "max.R.sq.fit", "max.Adj.R.sq.fit")
if (glb_is_classification) {
if (glb_is_binomial)
glbMdlMetricsEval <-
c("max.Accuracy.OOB", "max.AUCROCR.OOB", "max.AUCpROC.OOB", "min.aic.fit", "max.Accuracy.fit") else
glbMdlMetricsEval <- c("max.Accuracy.OOB", "max.Kappa.OOB")
}
# select from NULL [no ensemble models], "auto" [all models better than MFO or Baseline], c(mdl_ids in glb_models_lst) [Typically top-rated models in auto]
glb_mdl_ensemble <- NULL
# "%<d-% setdiff(mygetEnsembleAutoMdlIds(), 'CSM.X.rf')"
# c(<comma-separated-mdlIds>
# )
# Only for classifications; for regressions remove "(.*)\\.prob" form the regex
# tmp_fitobs_df <- glbObsFit[, grep(paste0("^", gsub(".", "\\.", mygetPredictIds$value, fixed = TRUE), "CSM\\.X\\.(.*)\\.prob"), names(glbObsFit), value = TRUE)]; cor_mtrx <- cor(tmp_fitobs_df); cor_vctr <- sort(cor_mtrx[row.names(orderBy(~-Overall, varImp(glb_models_lst[["Ensemble.repeatedcv.glmnet"]])$imp))[1], ]); summary(cor_vctr); cor_vctr
#ntv.glm <- glm(reformulate(indepVar, glb_rsp_var), family = "binomial", data = glbObsFit)
#step.glm <- step(ntv.glm)
glb_sel_mdl_id <- "All.X##rcv#glmnet" #select from c(NULL, "All.X##rcv#glmnet", "RFE.X##rcv#glmnet", <mdlId>)
glb_fin_mdl_id <- NULL #select from c(NULL, glb_sel_mdl_id)
glb_dsp_cols <- c(".pos", glbFeatsId, glbFeatsCategory, glb_rsp_var
# List critical cols excl. above
)
# Output specs
# lclgetfltout_df <- function(obsout_df) {
# require(tidyr)
# obsout_df <- obsout_df %>%
# tidyr::separate("ImageId.x.y", c(".src", ".pos", "x", "y"),
# sep = "#", remove = TRUE, extra = "merge")
# # mnm prefix stands for max_n_mean
# mnmout_df <- obsout_df %>%
# dplyr::group_by(.pos) %>%
# #dplyr::top_n(1, Probability1) %>% # Score = 3.9426
# #dplyr::top_n(2, Probability1) %>% # Score = ???; weighted = 3.94254;
# #dplyr::top_n(3, Probability1) %>% # Score = 3.9418; weighted = 3.94169;
# dplyr::top_n(4, Probability1) %>% # Score = ???; weighted = 3.94149;
# #dplyr::top_n(5, Probability1) %>% # Score = 3.9421; weighted = 3.94178
#
# # dplyr::summarize(xMeanN = mean(as.numeric(x)), yMeanN = mean(as.numeric(y)))
# # dplyr::summarize(xMeanN = weighted.mean(as.numeric(x), Probability1), yMeanN = mean(as.numeric(y)))
# # dplyr::summarize(xMeanN = weighted.mean(as.numeric(x), c(Probability1, 0.2357323, 0.2336925)), yMeanN = mean(as.numeric(y)))
# # dplyr::summarize(xMeanN = weighted.mean(as.numeric(x), c(Probability1)), yMeanN = mean(as.numeric(y)))
# dplyr::summarize(xMeanN = weighted.mean(as.numeric(x), c(Probability1)),
# yMeanN = weighted.mean(as.numeric(y), c(Probability1)))
#
# maxout_df <- obsout_df %>%
# dplyr::group_by(.pos) %>%
# dplyr::summarize(maxProb1 = max(Probability1))
# fltout_df <- merge(maxout_df, obsout_df,
# by.x = c(".pos", "maxProb1"), by.y = c(".pos", "Probability1"),
# all.x = TRUE)
# fmnout_df <- merge(fltout_df, mnmout_df,
# by.x = c(".pos"), by.y = c(".pos"),
# all.x = TRUE)
# return(fmnout_df)
# }
glbObsOut <- list(NULL
# glbFeatsId will be the first output column, by default
,vars = list()
# ,mapFn = function(obsout_df) {
# }
)
#obsout_df <- savobsout_df
# glbObsOut$mapFn <- function(obsout_df) {
# txfout_df <- dplyr::select(obsout_df, -.pos.y) %>%
# dplyr::mutate(
# lunch = levels(glbObsTrn[, "lunch" ])[
# round(mean(as.numeric(glbObsTrn[, "lunch" ])), 0)],
# dinner = levels(glbObsTrn[, "dinner" ])[
# round(mean(as.numeric(glbObsTrn[, "dinner" ])), 0)],
# reserve = levels(glbObsTrn[, "reserve" ])[
# round(mean(as.numeric(glbObsTrn[, "reserve" ])), 0)],
# outdoor = levels(glbObsTrn[, "outdoor" ])[
# round(mean(as.numeric(glbObsTrn[, "outdoor" ])), 0)],
# expensive = levels(glbObsTrn[, "expensive"])[
# round(mean(as.numeric(glbObsTrn[, "expensive"])), 0)],
# liquor = levels(glbObsTrn[, "liquor" ])[
# round(mean(as.numeric(glbObsTrn[, "liquor" ])), 0)],
# table = levels(glbObsTrn[, "table" ])[
# round(mean(as.numeric(glbObsTrn[, "table" ])), 0)],
# classy = levels(glbObsTrn[, "classy" ])[
# round(mean(as.numeric(glbObsTrn[, "classy" ])), 0)],
# kids = levels(glbObsTrn[, "kids" ])[
# round(mean(as.numeric(glbObsTrn[, "kids" ])), 0)]
# )
#
# print("ObsNew output class tables:")
# print(sapply(c("lunch","dinner","reserve","outdoor",
# "expensive","liquor","table",
# "classy","kids"),
# function(feat) table(txfout_df[, feat], useNA = "ifany")))
#
# txfout_df <- txfout_df %>%
# dplyr::mutate(labels = "") %>%
# dplyr::mutate(labels =
# ifelse(lunch != "-1", paste(labels, lunch ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(dinner != "-1", paste(labels, dinner ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(reserve != "-1", paste(labels, reserve ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(outdoor != "-1", paste(labels, outdoor ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(expensive != "-1", paste(labels, expensive), labels)) %>%
# dplyr::mutate(labels =
# ifelse(liquor != "-1", paste(labels, liquor ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(table != "-1", paste(labels, table ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(classy != "-1", paste(labels, classy ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(kids != "-1", paste(labels, kids ), labels)) %>%
# dplyr::select(business_id, labels)
# return(txfout_df)
# }
#if (!is.null(glbObsOut$mapFn)) obsout_df <- glbObsOut$mapFn(obsout_df); print(head(obsout_df))
glb_out_obs <- NULL # select from c(NULL : default to "new", "all", "new", "trn")
if (glb_is_classification && glb_is_binomial) {
glbObsOut$vars[["Probability1"]] <-
"%<d-% glbObsNew[, mygetPredictIds(glb_rsp_var, glb_fin_mdl_id)$prob]"
# glbObsOut$vars[[glb_rsp_var_raw]] <-
# "%<d-% glb_map_rsp_var_to_raw(glbObsNew[,
# mygetPredictIds(glb_rsp_var, glb_fin_mdl_id)$value])"
} else {
# glbObsOut$vars[[glbFeatsId]] <-
# "%<d-% as.integer(gsub('Test#', '', glbObsNew[, glbFeatsId]))"
glbObsOut$vars[[glb_rsp_var]] <-
"%<d-% glbObsNew[, mygetPredictIds(glb_rsp_var, glb_fin_mdl_id)$value]"
# for (outVar in setdiff(glbFeatsExcludeLcl, glb_rsp_var_raw))
# glbObsOut$vars[[outVar]] <-
# paste0("%<d-% mean(glbObsAll[, \"", outVar, "\"], na.rm = TRUE)")
}
# glbObsOut$vars[[glb_rsp_var_raw]] <- glb_rsp_var_raw
# glbObsOut$vars[[paste0(head(unlist(strsplit(mygetPredictIds$value, "")), -1), collapse = "")]] <-
glbOutStackFnames <- NULL #: default
# c("ebayipads_txt_assoc1_out_bid1_stack.csv") # manual stack
# c("ebayipads_finmdl_bid1_out_nnet_1.csv") # universal stack
glbOut <- list(pfx = "Stocks_BlueChips_2016_")
# lclImageSampleSeed <- 129
glbOutDataVizFname <- NULL # choose from c(NULL, "<projectId>_obsall.csv")
glbChunks <- list(labels = c("set_global_options_wd","set_global_options"
,"import.data","inspect.data","scrub.data","transform.data"
,"extract.features"
,"extract.features.datetime","extract.features.image","extract.features.price"
,"extract.features.text","extract.features.string"
,"extract.features.end"
,"manage.missing.data","cluster.data","partition.data.training","select.features"
,"fit.models_0","fit.models_1","fit.models_2","fit.models_3"
,"fit.data.training_0","fit.data.training_1"
,"predict.data.new"
,"display.session.info"))
# To ensure that all chunks in this script are in glbChunks
if (!is.null(chkChunksLabels <- knitr::all_labels()) && # knitr::all_labels() doesn't work in console runs
!identical(chkChunksLabels, glbChunks$labels)) {
print(sprintf("setdiff(chkChunksLabels, glbChunks$labels): %s",
setdiff(chkChunksLabels, glbChunks$labels)))
print(sprintf("setdiff(glbChunks$labels, chkChunksLabels): %s",
setdiff(glbChunks$labels, chkChunksLabels)))
}
glbChunks[["first"]] <- NULL #default: script will load envir from previous chunk
glbChunks[["last"]] <- NULL #"extract.features.end" #NULL #default: script will save envir at end of this chunk
#mysavChunk(glbOut$pfx, glbChunks[["last"]])
# Inspect max OOB FP
#chkObsOOB <- subset(glbObsOOB, !label.fctr.All.X..rcv.glmnet.is.acc)
#chkObsOOBFP <- subset(chkObsOOB, label.fctr.All.X..rcv.glmnet == "left_eye_center") %>% dplyr::mutate(Probability1 = label.fctr.All.X..rcv.glmnet.prob) %>% select(-.src, -.pos, -x, -y) %>% lclgetfltout_df() %>% mutate(obj.distance = (((as.numeric(x) - left_eye_center_x.int) ^ 2) + ((as.numeric(y) - left_eye_center_y.int) ^ 2)) ^ 0.5) %>% dplyr::top_n(5, obj.distance) %>% dplyr::top_n(5, -patch.cor)
#
#newImgObs <- glbObsNew[(glbObsNew$ImageId == "Test#0001"), ]; print(newImgObs[which.max(newImgObs$label.fctr.Final..rcv.glmnet.prob), ])
#OOBImgObs <- glbObsOOB[(glbObsOOB$ImageId == "Train#0003"), ]; print(OOBImgObs[which.max(OOBImgObs$label.fctr.All.X..rcv.glmnet.prob), ])
#load("Stocks_BlueChips_2016_extract.features.end.RData", verbose = TRUE)
#mygetImage(which(glbObsAll[, glbFeatsId] == "Train#0003"), names(glbFeatsImage)[1], plot = TRUE, featHighlight = c("left_eye_center_x", "left_eye_center_y"), ovrlHighlight = c(66, 35))
# Depict process
glb_analytics_pn <- petrinet(name = "glb_analytics_pn",
trans_df = data.frame(id = 1:6,
name = c("data.training.all","data.new",
"model.selected","model.final",
"data.training.all.prediction","data.new.prediction"),
x=c( -5,-5,-15,-25,-25,-35),
y=c( -5, 5, 0, 0, -5, 5)
),
places_df=data.frame(id=1:4,
name=c("bgn","fit.data.training.all","predict.data.new","end"),
x=c( -0, -20, -30, -40),
y=c( 0, 0, 0, 0),
M0=c( 3, 0, 0, 0)
),
arcs_df = data.frame(
begin = c("bgn","bgn","bgn",
"data.training.all","model.selected","fit.data.training.all",
"fit.data.training.all","model.final",
"data.new","predict.data.new",
"data.training.all.prediction","data.new.prediction"),
end = c("data.training.all","data.new","model.selected",
"fit.data.training.all","fit.data.training.all","model.final",
"data.training.all.prediction","predict.data.new",
"predict.data.new","data.new.prediction",
"end","end")
))
#print(ggplot.petrinet(glb_analytics_pn))
print(ggplot.petrinet(glb_analytics_pn) + coord_flip())## Loading required package: grid
glb_analytics_avl_objs <- NULL
glb_chunks_df <- myadd_chunk(NULL, "import.data")## label step_major step_minor label_minor bgn end elapsed
## 1 import.data 1 0 0 6.273 NA NAStep 1.0: import data
chunk option: eval=
## [1] "Reading file ./data/IBMStock.csv..."
## [1] "dimensions of data in ./data/IBMStock.csv: 480 rows x 2 cols"
## [1] "Reading file ./data/GEStock.csv..."
## [1] "dimensions of data in ./data/GEStock.csv: 480 rows x 2 cols"
## [1] "Reading file ./data/ProcterGambleStock.csv..."
## [1] "dimensions of data in ./data/ProcterGambleStock.csv: 480 rows x 2 cols"
## [1] "Reading file ./data/CocaColaStock.csv..."
## [1] "dimensions of data in ./data/CocaColaStock.csv: 480 rows x 2 cols"
## [1] "Reading file ./data/BoeingStock.csv..."
## [1] "dimensions of data in ./data/BoeingStock.csv: 480 rows x 2 cols"
## Date StockPrice .inp
## 1 1/1/70 360.3190 IBM
## 2 2/1/70 346.7237 IBM
## 3 3/1/70 327.3457 IBM
## 4 4/1/70 319.8527 IBM
## 5 5/1/70 270.3752 IBM
## 6 6/1/70 267.2050 IBM
## Date StockPrice .inp
## 83 11/1/76 267.15050 IBM
## 366 6/1/00 114.26818 IBM
## 1223 11/1/91 82.37900 PG
## 1746 6/1/95 62.29045 CC
## 1762 10/1/96 49.75217 CC
## 2374 10/1/07 98.90652 BG
## Date StockPrice .inp
## 2395 7/1/09 41.48273 BG
## 2396 8/1/09 45.99429 BG
## 2397 9/1/09 51.36286 BG
## 2398 10/1/09 51.15909 BG
## 2399 11/1/09 50.69650 BG
## 2400 12/1/09 55.02864 BG
## 'data.frame': 2400 obs. of 3 variables:
## $ Date : chr "1/1/70" "2/1/70" "3/1/70" "4/1/70" ...
## $ StockPrice: num 360 347 327 320 270 ...
## $ .inp : chr "IBM" "IBM" "IBM" "IBM" ...
## - attr(*, "comment")= chr "glbObsTrn"
## NULL## Warning: No file specified for glbObsNew & splitSpecs$method not specified.
## Defaulting to copy.## Date StockPrice .inp
## 1 1/1/70 360.3190 IBM
## 2 2/1/70 346.7237 IBM
## 3 3/1/70 327.3457 IBM
## 4 4/1/70 319.8527 IBM
## 5 5/1/70 270.3752 IBM
## 6 6/1/70 267.2050 IBM
## Date StockPrice .inp
## 3 3/1/70 327.34571 IBM
## 429 9/1/05 79.58857 IBM
## 931 7/1/07 39.39810 GE
## 939 3/1/08 34.80150 GE
## 965 5/1/70 73.33286 PG
## 1110 6/1/82 83.65682 PG
## Date StockPrice .inp
## 2395 7/1/09 41.48273 BG
## 2396 8/1/09 45.99429 BG
## 2397 9/1/09 51.36286 BG
## 2398 10/1/09 51.15909 BG
## 2399 11/1/09 50.69650 BG
## 2400 12/1/09 55.02864 BG
## 'data.frame': 2400 obs. of 3 variables:
## $ Date : chr "1/1/70" "2/1/70" "3/1/70" "4/1/70" ...
## $ StockPrice: num 360 347 327 320 270 ...
## $ .inp : chr "IBM" "IBM" "IBM" "IBM" ...
## - attr(*, "comment")= chr "glbObsNew"
## Date StockPrice .inp
## 1 1/1/70 360.3190 IBM
## 2 2/1/70 346.7237 IBM
## 3 3/1/70 327.3457 IBM
## 4 4/1/70 319.8527 IBM
## 5 5/1/70 270.3752 IBM
## 6 6/1/70 267.2050 IBM
## Date StockPrice .inp
## 784 4/1/95 54.98947 GE
## 1089 9/1/80 76.83714 PG
## 1544 8/1/78 45.08957 CC
## 1696 4/1/91 54.12682 CC
## 2284 4/1/00 37.15211 BG
## 2315 11/1/02 32.19400 BG
## Date StockPrice .inp
## 2395 7/1/09 41.48273 BG
## 2396 8/1/09 45.99429 BG
## 2397 9/1/09 51.36286 BG
## 2398 10/1/09 51.15909 BG
## 2399 11/1/09 50.69650 BG
## 2400 12/1/09 55.02864 BG
## 'data.frame': 2400 obs. of 3 variables:
## $ Date : chr "1/1/70" "2/1/70" "3/1/70" "4/1/70" ...
## $ StockPrice: num 360 347 327 320 270 ...
## $ .inp : chr "IBM" "IBM" "IBM" "IBM" ...
## - attr(*, "comment")= chr "glbObsTrn"## Warning: glbObsTrn same as glbObsAll## Warning: glbObsNew same as glbObsAll## [1] "Creating new feature: .pos..."
## [1] "Creating new feature: .pos.y..."## Warning: using .rownames as identifiers for observations## [1] "Partition stats:"## Loading required package: sqldf## Loading required package: gsubfn## Loading required package: proto## Loading required package: RSQLite## Loading required package: DBI## Loading required package: tcltk## StockPrice.cut.fctr .src .n
## 1 (8.86,152] Test 2269
## 2 (8.86,152] Train 2269
## 3 (152,296] Test 88
## 4 (152,296] Train 88
## 5 (296,439] Test 43
## 6 (296,439] Train 43
## StockPrice.cut.fctr .src .n
## 1 (8.86,152] Test 2269
## 2 (8.86,152] Train 2269
## 3 (152,296] Test 88
## 4 (152,296] Train 88
## 5 (296,439] Test 43
## 6 (296,439] Train 43## Loading required package: RColorBrewer
## .src .n
## 1 Test 2400
## 2 Train 2400## Loading required package: lazyeval## Loading required package: gdata## gdata: read.xls support for 'XLS' (Excel 97-2004) files ENABLED.## ## gdata: read.xls support for 'XLSX' (Excel 2007+) files ENABLED.##
## Attaching package: 'gdata'## The following objects are masked from 'package:dplyr':
##
## combine, first, last## The following object is masked from 'package:stats':
##
## nobs## The following object is masked from 'package:utils':
##
## object.size## [1] "Found 0 duplicates by all features:"## NULL## label step_major step_minor label_minor bgn end elapsed
## 1 import.data 1 0 0 6.273 8.854 2.581
## 2 inspect.data 2 0 0 8.854 NA NAStep 2.0: inspect data
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## [1] "numeric data missing in glbObsAll: "
## named integer(0)
## [1] "numeric data w/ 0s in glbObsAll: "
## named integer(0)
## [1] "numeric data w/ Infs in glbObsAll: "
## named integer(0)
## [1] "numeric data w/ NaNs in glbObsAll: "
## named integer(0)
## [1] "string data missing in glbObsAll: "
## Date .inp
## 0 0
## NULL## label step_major step_minor label_minor bgn end elapsed
## 2 inspect.data 2 0 0 8.854 48.69 39.836
## 3 scrub.data 2 1 1 48.691 NA NAStep 2.1: scrub data
## [1] "numeric data missing in glbObsAll: "
## named integer(0)
## [1] "numeric data w/ 0s in glbObsAll: "
## named integer(0)
## [1] "numeric data w/ Infs in glbObsAll: "
## named integer(0)
## [1] "numeric data w/ NaNs in glbObsAll: "
## named integer(0)
## [1] "string data missing in glbObsAll: "
## Date .inp
## 0 0## label step_major step_minor label_minor bgn end elapsed
## 3 scrub.data 2 1 1 48.691 76.225 27.534
## 4 transform.data 2 2 2 76.226 NA NAStep 2.2: transform data
## label step_major step_minor label_minor bgn end elapsed
## 4 transform.data 2 2 2 76.226 76.267 0.041
## 5 extract.features 3 0 0 76.267 NA NAStep 3.0: extract features
## label step_major step_minor label_minor bgn
## 5 extract.features 3 0 0 76.267
## 6 extract.features.datetime 3 1 1 76.288
## end elapsed
## 5 76.288 0.021
## 6 NA NAStep 3.1: extract features datetime
## label step_major step_minor label_minor bgn
## 1 extract.features.datetime.bgn 1 0 0 76.315
## end elapsed
## 1 NA NA## label step_major step_minor label_minor
## 1 extract.features.datetime.bgn 1 0 0
## 2 extract.features_xtract.DateTime.vars 2 0 0
## bgn end elapsed
## 1 76.315 76.322 0.008
## 2 76.323 NA NA
## [1] "Extracting features from DateTime(s): Date"
## Loading required package: XML## [1] " accessing url: http://about.usps.com/news/events-calendar/1970-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1970-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1971-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1971-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1972-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1972-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1973-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1973-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1974-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1974-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1975-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1975-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1976-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1976-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1977-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1977-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1978-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1978-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1979-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1979-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1980-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1980-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1981-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1981-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1982-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1982-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1983-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1983-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1984-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1984-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1985-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1985-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1986-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1986-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1987-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1987-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1988-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1988-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1989-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1989-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1990-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1990-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1991-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1991-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1992-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1992-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1993-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1993-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1994-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1994-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1995-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1995-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1996-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1996-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1997-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1997-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1998-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1998-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/1999-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/1999-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/2000-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/2000-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/2001-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/2001-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/2002-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/2002-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/2003-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/2003-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/2004-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/2004-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/2005-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/2005-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/2006-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/2006-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/2007-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/2007-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/2008-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/2008-federal-holidays.htm; skipping ...## [1] " accessing url: http://about.usps.com/news/events-calendar/2009-federal-holidays.htm"## Warning in myextract_dates_df(df = glbObsAll, vars =
## names(glbFeatsDateTime), : unable to access url:http://about.usps.com/news/
## events-calendar/2009-federal-holidays.htm; skipping ...
## [1] "**********"
## [1] "Consider adding state & city holidays for glbFeatsDateTime: Date"
## [1] "**********"
## Loading required package: zoo##
## Attaching package: 'zoo'## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric## [1] "Missing data for numerics:"
## Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p
## 2 4 8 16
## Date.last32.log1p
## 32## Loading required package: mice## Loading required package: Rcpp## mice 2.25 2015-11-09
## [1] "Summary before imputation: "
## Date .inp .src
## Length:4800 Length:4800 Length:4800
## Class :character Class :character Class :character
## Mode :character Mode :character Mode :character
##
##
##
##
## .rnorm .pos .pos.y .rownames
## Min. :-3.89398 Min. : 1 Min. : 1 Min. : 1
## 1st Qu.:-0.68672 1st Qu.:1201 1st Qu.:1201 1st Qu.:1201
## Median : 0.01802 Median :2400 Median :2400 Median :2400
## Mean : 0.00897 Mean :2400 Mean :2400 Mean :2400
## 3rd Qu.: 0.69953 3rd Qu.:3600 3rd Qu.:3600 3rd Qu.:3600
## Max. : 3.74468 Max. :4800 Max. :4800 Max. :4800
##
## Date.year.fctr Date.month.fctr Date.date.fctr Date.juliandate
## 1970 : 120 01 : 400 (0.999,0.9994] : 0 Min. : 1.0
## 1971 : 120 02 : 400 (0.9994,0.9998]: 0 1st Qu.: 83.5
## 1972 : 120 03 : 400 (0.9998,1.0002]:4800 Median :167.5
## 1973 : 120 04 : 400 (1.0002,1.0006]: 0 Mean :167.7
## 1974 : 120 05 : 400 (1.0006,1.001] : 0 3rd Qu.:252.2
## 1975 : 120 06 : 400 Max. :336.0
## (Other):4080 (Other):2400
## Date.wkday.fctr Date.wkend Date.hlday Date.hour.fctr
## 0:690 Min. :0.0000 Min. :0 Min. :0
## 1:680 1st Qu.:0.0000 1st Qu.:0 1st Qu.:0
## 2:690 Median :0.0000 Median :0 Median :0
## 3:680 Mean :0.2875 Mean :0 Mean :0
## 4:700 3rd Qu.:1.0000 3rd Qu.:0 3rd Qu.:0
## 5:670 Max. :1.0000 Max. :0 Max. :0
## 6:690
## Date.minute.fctr Date.second.fctr Date.day.minutes .order
## Min. :0 Min. :0 Min. :0 Min. : 1
## 1st Qu.:0 1st Qu.:0 1st Qu.:0 1st Qu.:1201
## Median :0 Median :0 Median :0 Median :2400
## Mean :0 Mean :0 Mean :0 Mean :2400
## 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0 3rd Qu.:3600
## Max. :0 Max. :0 Max. :0 Max. :4800
##
## Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p
## Min. : 0.000 Min. : 0.000 Min. : 0.00 Min. :14.70
## 1st Qu.: 0.000 1st Qu.: 0.000 1st Qu.:14.70 1st Qu.:14.80
## Median : 0.000 Median : 0.000 Median :14.77 Median :15.46
## Mean : 2.951 Mean : 5.905 Mean :11.82 Mean :15.20
## 3rd Qu.: 0.000 3rd Qu.:14.768 3rd Qu.:14.80 3rd Qu.:15.48
## Max. :14.802 Max. :14.802 Max. :14.80 Max. :15.49
## NA's :2 NA's :4 NA's :8 NA's :16
## Date.last32.log1p
## Min. :15.85
## 1st Qu.:15.88
## Median :15.89
## Mean :15.94
## 3rd Qu.:15.89
## Max. :16.18
## NA's :32
##
## iter imp variable
## 1 1 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 1 2 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 1 3 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 1 4 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 1 5 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 2 1 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 2 2 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 2 3 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 2 4 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 2 5 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 3 1 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 3 2 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 3 3 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 3 4 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 3 5 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 4 1 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 4 2 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 4 3 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 4 4 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 4 5 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 5 1 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 5 2 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 5 3 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 5 4 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 5 5 Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## .rnorm .pos .pos.y .rownames
## Min. :-3.89398 Min. : 1 Min. : 1 Min. : 1
## 1st Qu.:-0.68672 1st Qu.:1201 1st Qu.:1201 1st Qu.:1201
## Median : 0.01802 Median :2400 Median :2400 Median :2400
## Mean : 0.00897 Mean :2400 Mean :2400 Mean :2400
## 3rd Qu.: 0.69953 3rd Qu.:3600 3rd Qu.:3600 3rd Qu.:3600
## Max. : 3.74468 Max. :4800 Max. :4800 Max. :4800
##
## Date.year.fctr Date.month.fctr Date.date.fctr Date.juliandate
## 1970 : 120 01 : 400 (0.999,0.9994] : 0 Min. : 1.0
## 1971 : 120 02 : 400 (0.9994,0.9998]: 0 1st Qu.: 83.5
## 1972 : 120 03 : 400 (0.9998,1.0002]:4800 Median :167.5
## 1973 : 120 04 : 400 (1.0002,1.0006]: 0 Mean :167.7
## 1974 : 120 05 : 400 (1.0006,1.001] : 0 3rd Qu.:252.2
## 1975 : 120 06 : 400 Max. :336.0
## (Other):4080 (Other):2400
## Date.wkday.fctr Date.wkend Date.hlday Date.hour.fctr
## 0:690 Min. :0.0000 Min. :0 Min. :0
## 1:680 1st Qu.:0.0000 1st Qu.:0 1st Qu.:0
## 2:690 Median :0.0000 Median :0 Median :0
## 3:680 Mean :0.2875 Mean :0 Mean :0
## 4:700 3rd Qu.:1.0000 3rd Qu.:0 3rd Qu.:0
## 5:670 Max. :1.0000 Max. :0 Max. :0
## 6:690
## Date.minute.fctr Date.second.fctr Date.day.minutes .order
## Min. :0 Min. :0 Min. :0 Min. : 1
## 1st Qu.:0 1st Qu.:0 1st Qu.:0 1st Qu.:1201
## Median :0 Median :0 Median :0 Median :2400
## Mean :0 Mean :0 Mean :0 Mean :2400
## 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0 3rd Qu.:3600
## Max. :0 Max. :0 Max. :0 Max. :4800
##
## Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p
## Min. : 0.000 Min. : 0.000 Min. : 0.00 Min. :14.70
## 1st Qu.: 0.000 1st Qu.: 0.000 1st Qu.:14.70 1st Qu.:14.80
## Median : 0.000 Median : 0.000 Median :14.77 Median :15.46
## Mean : 2.956 Mean : 5.913 Mean :11.83 Mean :15.20
## 3rd Qu.: 0.000 3rd Qu.:14.768 3rd Qu.:14.80 3rd Qu.:15.48
## Max. :14.802 Max. :14.802 Max. :14.80 Max. :15.49
##
## Date.last32.log1p
## Min. :15.85
## 1st Qu.:15.88
## Median :15.89
## Mean :15.94
## 3rd Qu.:15.89
## Max. :16.18
## 
## label step_major step_minor label_minor bgn
## 6 extract.features.datetime 3 1 1 76.288
## 7 extract.features.image 3 2 2 110.590
## end elapsed
## 6 110.59 34.302
## 7 NA NAStep 3.2: extract features image
```{r extract.features.image, cache=FALSE, echo=FALSE, fig.height=5, fig.width=5, eval=myevlChunk(glbChunks, glbOut$pfx)}
## label step_major step_minor label_minor bgn end
## 1 extract.features.image.bgn 1 0 0 114.074 NA
## elapsed
## 1 NA## label step_major step_minor label_minor bgn
## 1 extract.features.image.bgn 1 0 0 114.074
## 2 extract.features.image.end 2 0 0 114.084
## end elapsed
## 1 114.083 0.01
## 2 NA NA## label step_major step_minor label_minor bgn
## 1 extract.features.image.bgn 1 0 0 114.074
## 2 extract.features.image.end 2 0 0 114.084
## end elapsed
## 1 114.083 0.01
## 2 NA NA## label step_major step_minor label_minor bgn end
## 7 extract.features.image 3 2 2 110.590 114.094
## 8 extract.features.price 3 3 3 114.094 NA
## elapsed
## 7 3.504
## 8 NAStep 3.3: extract features price
## label step_major step_minor label_minor bgn end
## 1 extract.features.price.bgn 1 0 0 114.122 NA
## elapsed
## 1 NA## label step_major step_minor label_minor bgn end
## 8 extract.features.price 3 3 3 114.094 114.132
## 9 extract.features.text 3 4 4 114.133 NA
## elapsed
## 8 0.039
## 9 NAStep 3.4: extract features text
## label step_major step_minor label_minor bgn end
## 1 extract.features.text.bgn 1 0 0 114.177 NA
## elapsed
## 1 NA## label step_major step_minor label_minor bgn
## 9 extract.features.text 3 4 4 114.133
## 10 extract.features.string 3 5 5 114.187
## end elapsed
## 9 114.186 0.053
## 10 NA NAStep 3.5: extract features string
## label step_major step_minor label_minor bgn
## 1 extract.features.string.bgn 1 0 0 114.219
## end elapsed
## 1 NA NA## label step_major step_minor
## 1 extract.features.string.bgn 1 0
## 2 extract.features.stringfactorize.str.vars 2 0
## label_minor bgn end elapsed
## 1 0 114.219 114.229 0.011
## 2 0 114.230 NA NA## Date .inp .src
## "Date" ".inp" ".src"## Warning: Creating factors of string variable: .inp: # of unique values: 5## label step_major step_minor label_minor bgn
## 10 extract.features.string 3 5 5 114.187
## 11 extract.features.end 3 6 6 114.247
## end elapsed
## 10 114.247 0.06
## 11 NA NAStep 3.6: extract features end
## time trans "bgn " "fit.data.training.all " "predict.data.new " "end "
## 0.0000 multiple enabled transitions: data.training.all data.new model.selected firing: data.training.all
## 1.0000 1 2 1 0 0
## 1.0000 multiple enabled transitions: data.training.all data.new model.selected model.final data.training.all.prediction firing: data.new
## 2.0000 2 1 1 1 0
## label step_major step_minor label_minor bgn end
## 11 extract.features.end 3 6 6 114.247 115.16
## 12 manage.missing.data 4 0 0 115.160 NA
## elapsed
## 11 0.913
## 12 NAStep 4.0: manage missing data
## [1] "numeric data missing in : "
## named integer(0)
## [1] "numeric data w/ 0s in : "
## Date.wkday.fctr Date.wkend Date.hlday Date.hour.fctr
## 690 3420 4800 4800
## Date.minute.fctr Date.second.fctr Date.day.minutes Date.last2.log1p
## 4800 4800 4800 3840
## Date.last4.log1p Date.last8.log1p
## 2880 960
## [1] "numeric data w/ Infs in : "
## named integer(0)
## [1] "numeric data w/ NaNs in : "
## named integer(0)
## [1] "string data missing in : "
## Date .inp
## 0 0## [1] "numeric data missing in : "
## named integer(0)
## [1] "numeric data w/ 0s in : "
## Date.wkday.fctr Date.wkend Date.hlday Date.hour.fctr
## 690 3420 4800 4800
## Date.minute.fctr Date.second.fctr Date.day.minutes Date.last2.log1p
## 4800 4800 4800 3840
## Date.last4.log1p Date.last8.log1p
## 2880 960
## [1] "numeric data w/ Infs in : "
## named integer(0)
## [1] "numeric data w/ NaNs in : "
## named integer(0)
## [1] "string data missing in : "
## Date .inp
## 0 0## label step_major step_minor label_minor bgn end
## 12 manage.missing.data 4 0 0 115.160 115.476
## 13 cluster.data 5 0 0 115.476 NA
## elapsed
## 12 0.316
## 13 NAStep 5.0: cluster data
## label step_major step_minor label_minor bgn
## 13 cluster.data 5 0 0 115.476
## 14 partition.data.training 6 0 0 115.529
## end elapsed
## 13 115.529 0.053
## 14 NA NAStep 6.0: partition data training
## [1] "partition.data.training chunk: setup: elapsed: 0.00 secs"## [1] "Newdata contains non-NA data for StockPrice; setting OOB to Newdata"## [1] "partition.data.training chunk: Fit/OOB partition complete: elapsed: 0.01 secs"## .inp .n.Fit .n.OOB .n.Tst .freqRatio.Fit .freqRatio.OOB .freqRatio.Tst
## 1 BG 480 480 480 0.2 0.2 0.2
## 2 CC 480 480 480 0.2 0.2 0.2
## 3 GE 480 480 480 0.2 0.2 0.2
## 4 IBM 480 480 480 0.2 0.2 0.2
## 5 PG 480 480 480 0.2 0.2 0.2## [1] "glbObsAll: "## [1] 4800 28## [1] "glbObsTrn: "## [1] 2400 28## [1] "glbObsFit: "## [1] 2400 27## [1] "glbObsOOB: "## [1] 2400 27## [1] "glbObsNew: "## [1] 2400 27## [1] "partition.data.training chunk: teardown: elapsed: 0.22 secs"## label step_major step_minor label_minor bgn
## 14 partition.data.training 6 0 0 115.529
## 15 select.features 7 0 0 115.812
## end elapsed
## 14 115.811 0.282
## 15 NA NAStep 7.0: select features
## Warning in cor(data.matrix(entity_df[, sel_feats]), y =
## as.numeric(entity_df[, : the standard deviation is zero## Loading required package: reshape2## [1] "cor(.pos, .pos.y)=1.0000"
## [1] "cor(StockPrice, .pos)=-0.5304"
## [1] "cor(StockPrice, .pos.y)=-0.5304"## Warning in myfind_cor_features(feats_df = glb_feats_df, obs_df =
## glbObsTrn, : Identified .pos.y as highly correlated with .pos## [1] "cor(.pos, .rownames)=1.0000"
## [1] "cor(StockPrice, .pos)=-0.5304"
## [1] "cor(StockPrice, .rownames)=-0.5304"## Warning in myfind_cor_features(feats_df = glb_feats_df, obs_df =
## glbObsTrn, : Identified .rownames as highly correlated with .pos## [1] "cor(Date.juliandate, Date.month.fctr)=1.0000"
## [1] "cor(StockPrice, Date.juliandate)=-0.0337"
## [1] "cor(StockPrice, Date.month.fctr)=-0.0337"## Warning in myfind_cor_features(feats_df = glb_feats_df, obs_df =
## glbObsTrn, : Identified Date.juliandate as highly correlated with
## Date.month.fctr## [1] "cor(Date.last2.log1p, Date.last32.log1p)=0.9976"
## [1] "cor(StockPrice, Date.last2.log1p)=0.3532"
## [1] "cor(StockPrice, Date.last32.log1p)=0.3511"## Warning in myfind_cor_features(feats_df = glb_feats_df, obs_df =
## glbObsTrn, : Identified Date.last32.log1p as highly correlated with
## Date.last2.log1p## [1] "cor(.pos, Date.last2.log1p)=-0.8485"
## [1] "cor(StockPrice, .pos)=-0.5304"
## [1] "cor(StockPrice, Date.last2.log1p)=0.3532"## Warning in myfind_cor_features(feats_df = glb_feats_df, obs_df =
## glbObsTrn, : Identified Date.last2.log1p as highly correlated with .pos## [1] "cor(.inp.fctr, Date.last4.log1p)=0.7071"
## [1] "cor(StockPrice, .inp.fctr)=0.3700"
## [1] "cor(StockPrice, Date.last4.log1p)=0.2767"## Warning in myfind_cor_features(feats_df = glb_feats_df, obs_df
## = glbObsTrn, : Identified Date.last4.log1p as highly correlated
## with .inp.fctr## cor.y exclude.as.feat cor.y.abs
## .inp.fctr 3.699980e-01 0 3.699980e-01
## Date.last2.log1p 3.532134e-01 0 3.532134e-01
## Date.last32.log1p 3.510897e-01 0 3.510897e-01
## Date.last4.log1p 2.767099e-01 0 2.767099e-01
## Date.wkday.fctr 6.166083e-03 0 6.166083e-03
## Date.wkend -6.905542e-05 0 6.905542e-05
## .rnorm -1.152039e-03 0 1.152039e-03
## Date.last8.log1p -1.182108e-02 0 1.182108e-02
## Date.last16.log1p -3.163526e-02 0 3.163526e-02
## Date.juliandate -3.365921e-02 0 3.365921e-02
## Date.month.fctr -3.367924e-02 0 3.367924e-02
## Date.year.fctr -2.415176e-01 1 2.415176e-01
## Date.POSIX -2.422818e-01 1 2.422818e-01
## Date.zoo -5.303143e-01 1 5.303143e-01
## .pos -5.303686e-01 0 5.303686e-01
## .pos.y -5.303686e-01 0 5.303686e-01
## .rownames -5.303686e-01 0 5.303686e-01
## Date.date.fctr NA 0 NA
## Date.day.minutes NA 1 NA
## Date.hlday NA 0 NA
## Date.hour.fctr NA 0 NA
## Date.minute.fctr NA 0 NA
## Date.second.fctr NA 0 NA
## cor.high.X freqRatio percentUnique zeroVar nzv
## .inp.fctr <NA> 1.000000 0.20833333 FALSE FALSE
## Date.last2.log1p .pos 3.025210 0.41666667 FALSE FALSE
## Date.last32.log1p Date.last2.log1p 2.046610 0.87500000 FALSE FALSE
## Date.last4.log1p .inp.fctr 1.959016 0.41666667 FALSE FALSE
## Date.wkday.fctr <NA> 1.014493 0.29166667 FALSE FALSE
## Date.wkend <NA> 2.478261 0.08333333 FALSE FALSE
## .rnorm <NA> 1.000000 100.00000000 FALSE FALSE
## Date.last8.log1p <NA> 1.949264 0.37500000 FALSE FALSE
## Date.last16.log1p <NA> 2.116456 0.37500000 FALSE FALSE
## Date.juliandate Date.month.fctr 1.000000 0.91666667 FALSE FALSE
## Date.month.fctr <NA> 1.000000 0.50000000 FALSE FALSE
## Date.year.fctr <NA> 1.000000 1.66666667 FALSE FALSE
## Date.POSIX <NA> 1.000000 20.00000000 FALSE FALSE
## Date.zoo <NA> 1.000000 10.00000000 FALSE FALSE
## .pos <NA> 1.000000 100.00000000 FALSE FALSE
## .pos.y .pos 1.000000 100.00000000 FALSE FALSE
## .rownames .pos 1.000000 100.00000000 FALSE FALSE
## Date.date.fctr <NA> 0.000000 0.04166667 TRUE TRUE
## Date.day.minutes <NA> 0.000000 0.04166667 TRUE TRUE
## Date.hlday <NA> 0.000000 0.04166667 TRUE TRUE
## Date.hour.fctr <NA> 0.000000 0.04166667 TRUE TRUE
## Date.minute.fctr <NA> 0.000000 0.04166667 TRUE TRUE
## Date.second.fctr <NA> 0.000000 0.04166667 TRUE TRUE
## is.cor.y.abs.low
## .inp.fctr FALSE
## Date.last2.log1p FALSE
## Date.last32.log1p FALSE
## Date.last4.log1p FALSE
## Date.wkday.fctr FALSE
## Date.wkend TRUE
## .rnorm FALSE
## Date.last8.log1p FALSE
## Date.last16.log1p FALSE
## Date.juliandate FALSE
## Date.month.fctr FALSE
## Date.year.fctr FALSE
## Date.POSIX FALSE
## Date.zoo FALSE
## .pos FALSE
## .pos.y FALSE
## .rownames FALSE
## Date.date.fctr NA
## Date.day.minutes NA
## Date.hlday NA
## Date.hour.fctr NA
## Date.minute.fctr NA
## Date.second.fctr NA## Warning in myplot_scatter(plt_feats_df, "percentUnique", "freqRatio",
## colorcol_name = "nzv", : converting nzv to class:factor## Warning: Removed 4 rows containing missing values (geom_point).
## Warning: Removed 4 rows containing missing values (geom_point).
## Warning: Removed 4 rows containing missing values (geom_point).
## cor.y exclude.as.feat cor.y.abs cor.high.X freqRatio
## Date.date.fctr NA 0 NA <NA> 0
## Date.day.minutes NA 1 NA <NA> 0
## Date.hlday NA 0 NA <NA> 0
## Date.hour.fctr NA 0 NA <NA> 0
## Date.minute.fctr NA 0 NA <NA> 0
## Date.second.fctr NA 0 NA <NA> 0
## percentUnique zeroVar nzv is.cor.y.abs.low
## Date.date.fctr 0.04166667 TRUE TRUE NA
## Date.day.minutes 0.04166667 TRUE TRUE NA
## Date.hlday 0.04166667 TRUE TRUE NA
## Date.hour.fctr 0.04166667 TRUE TRUE NA
## Date.minute.fctr 0.04166667 TRUE TRUE NA
## Date.second.fctr 0.04166667 TRUE TRUE NA
## [1] "numeric data missing in : "
## named integer(0)
## [1] "numeric data w/ 0s in : "
## Date.wkday.fctr Date.wkend Date.hlday Date.hour.fctr
## 690 3420 4800 4800
## Date.minute.fctr Date.second.fctr Date.day.minutes Date.last2.log1p
## 4800 4800 4800 3840
## Date.last4.log1p Date.last8.log1p
## 2880 960
## [1] "numeric data w/ Infs in : "
## named integer(0)
## [1] "numeric data w/ NaNs in : "
## named integer(0)
## [1] "string data missing in : "
## Date .inp .lcn
## 0 0 0## [1] "glb_feats_df:"## [1] 23 12## id exclude.as.feat rsp_var
## StockPrice StockPrice TRUE TRUE## id cor.y exclude.as.feat cor.y.abs cor.high.X freqRatio
## StockPrice StockPrice NA TRUE NA <NA> NA
## percentUnique zeroVar nzv is.cor.y.abs.low interaction.feat
## StockPrice NA NA NA NA NA
## shapiro.test.p.value rsp_var_raw rsp_var
## StockPrice NA NA TRUE## [1] "glb_feats_df vs. glbObsAll: "## character(0)## [1] "glbObsAll vs. glb_feats_df: "## character(0)## label step_major step_minor label_minor bgn end
## 15 select.features 7 0 0 115.812 117.848
## 16 fit.models 8 0 0 117.848 NA
## elapsed
## 15 2.036
## 16 NAStep 8.0: fit models
fit.models_0_chunk_df <- myadd_chunk(NULL, "fit.models_0_bgn", label.minor = "setup")## label step_major step_minor label_minor bgn end elapsed
## 1 fit.models_0_bgn 1 0 setup 118.407 NA NA# load(paste0(glbOut$pfx, "dsk.RData"))
get_model_sel_frmla <- function() {
model_evl_terms <- c(NULL)
# min.aic.fit might not be avl
lclMdlEvlCriteria <-
glbMdlMetricsEval[glbMdlMetricsEval %in% names(glb_models_df)]
for (metric in lclMdlEvlCriteria)
model_evl_terms <- c(model_evl_terms,
ifelse(length(grep("max", metric)) > 0, "-", "+"), metric)
if (glb_is_classification && glb_is_binomial)
model_evl_terms <- c(model_evl_terms, "-", "opt.prob.threshold.OOB")
model_sel_frmla <- as.formula(paste(c("~ ", model_evl_terms), collapse = " "))
return(model_sel_frmla)
}
get_dsp_models_df <- function() {
dsp_models_cols <- c("id",
glbMdlMetricsEval[glbMdlMetricsEval %in% names(glb_models_df)],
grep("opt.", names(glb_models_df), fixed = TRUE, value = TRUE))
dsp_models_df <-
#orderBy(get_model_sel_frmla(), glb_models_df)[, c("id", glbMdlMetricsEval)]
orderBy(get_model_sel_frmla(), glb_models_df)[, dsp_models_cols]
nCvMdl <- sapply(glb_models_lst, function(mdl) nrow(mdl$results))
nParams <- sapply(glb_models_lst, function(mdl) ifelse(mdl$method == "custom", 0,
nrow(subset(modelLookup(mdl$method), parameter != "parameter"))))
# nCvMdl <- nCvMdl[names(nCvMdl) != "avNNet"]
# nParams <- nParams[names(nParams) != "avNNet"]
if (length(cvMdlProblems <- nCvMdl[nCvMdl <= nParams]) > 0) {
print("Cross Validation issues:")
warning("Cross Validation issues:")
print(cvMdlProblems)
}
pltMdls <- setdiff(names(nCvMdl), names(cvMdlProblems))
pltMdls <- setdiff(pltMdls, names(nParams[nParams == 0]))
# length(pltMdls) == 21
png(paste0(glbOut$pfx, "bestTune.png"), width = 480 * 2, height = 480 * 4)
grid.newpage()
pushViewport(viewport(layout = grid.layout(ceiling(length(pltMdls) / 2.0), 2)))
pltIx <- 1
for (mdlId in pltMdls) {
print(ggplot(glb_models_lst[[mdlId]], highBestTune = TRUE) + labs(title = mdlId),
vp = viewport(layout.pos.row = ceiling(pltIx / 2.0),
layout.pos.col = ((pltIx - 1) %% 2) + 1))
pltIx <- pltIx + 1
}
dev.off()
if (all(row.names(dsp_models_df) != dsp_models_df$id))
row.names(dsp_models_df) <- dsp_models_df$id
return(dsp_models_df)
}
#get_dsp_models_df()
if (glb_is_classification && glb_is_binomial &&
(length(unique(glbObsFit[, glb_rsp_var])) < 2))
stop("glbObsFit$", glb_rsp_var, ": contains less than 2 unique values: ",
paste0(unique(glbObsFit[, glb_rsp_var]), collapse=", "))
max_cor_y_x_vars <- orderBy(~ -cor.y.abs,
subset(glb_feats_df, (exclude.as.feat == 0) & !nzv & !is.cor.y.abs.low &
is.na(cor.high.X)))[1:2, "id"]
max_cor_y_x_vars <- max_cor_y_x_vars[!is.na(max_cor_y_x_vars)]
if (length(max_cor_y_x_vars) < 2)
max_cor_y_x_vars <- union(max_cor_y_x_vars, ".pos")
if (!is.null(glb_Baseline_mdl_var)) {
if ((max_cor_y_x_vars[1] != glb_Baseline_mdl_var) &
(glb_feats_df[glb_feats_df$id == max_cor_y_x_vars[1], "cor.y.abs"] >
glb_feats_df[glb_feats_df$id == glb_Baseline_mdl_var, "cor.y.abs"]))
stop(max_cor_y_x_vars[1], " has a higher correlation with ", glb_rsp_var,
" than the Baseline var: ", glb_Baseline_mdl_var)
}
glb_model_type <- ifelse(glb_is_regression, "regression", "classification")
# Model specs
# c("id.prefix", "method", "type",
# # trainControl params
# "preProc.method", "cv.n.folds", "cv.n.repeats", "summary.fn",
# # train params
# "metric", "metric.maximize", "tune.df")
# Baseline
if (!is.null(glb_Baseline_mdl_var)) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Baseline"), major.inc = FALSE,
label.minor = "mybaseln_classfr")
ret_lst <- myfit_mdl(mdl_id="Baseline",
model_method="mybaseln_classfr",
indepVar=glb_Baseline_mdl_var,
rsp_var=glb_rsp_var,
fit_df=glbObsFit, OOB_df=glbObsOOB)
}
# Most Frequent Outcome "MFO" model: mean(y) for regression
# Not using caret's nullModel since model stats not avl
# Cannot use rpart for multinomial classification since it predicts non-MFO
if (glb_is_classification) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "MFO"), major.inc = FALSE,
label.minor = "myMFO_classfr")
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "MFO", type = glb_model_type, trainControl.method = "none",
train.method = ifelse(glb_is_regression, "lm", "myMFO_classfr"))),
indepVar = ".rnorm", rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
# "random" model - only for classification;
# none needed for regression since it is same as MFO
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Random"), major.inc = FALSE,
label.minor = "myrandom_classfr")
#stop(here"); glb2Sav(); all.equal(glb_models_df, sav_models_df)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Random", type = glb_model_type, trainControl.method = "none",
train.method = "myrandom_classfr")),
indepVar = ".rnorm", rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}
# Max.cor.Y
# Check impact of cv
# rpart is not a good candidate since caret does not optimize cp (only tuning parameter of rpart) well
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Max.cor.Y.rcv.*X*"), major.inc = FALSE,
label.minor = "glmnet")## label step_major step_minor label_minor bgn
## 1 fit.models_0_bgn 1 0 setup 118.407
## 2 fit.models_0_Max.cor.Y.rcv.*X* 1 1 glmnet 118.444
## end elapsed
## 1 118.444 0.037
## 2 NA NAret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.rcv.1X1", type = glb_model_type, trainControl.method = "none",
train.method = "glmnet")),
indepVar = max_cor_y_x_vars, rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: Max.cor.Y.rcv.1X1###glmnet"
## [1] " indepVar: .pos,.inp.fctr"
## [1] "myfit_mdl: setup complete: 1.007000 secs"## Loading required package: glmnet## Loading required package: Matrix## Loaded glmnet 2.0-5## Fitting alpha = 0.1, lambda = 0.668 on full training set
## [1] "myfit_mdl: train complete: 1.670000 secs"
## Length Class Mode
## a0 100 -none- numeric
## beta 500 dgCMatrix S4
## df 100 -none- numeric
## dim 2 -none- numeric
## lambda 100 -none- numeric
## dev.ratio 100 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 5 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 1 -none- logical
## [1] "min lambda > lambdaOpt:"
## (Intercept) .inp.fctrCC .inp.fctrGE .inp.fctrIBM .inp.fctrPG
## 168.3066609 -12.0627130 -67.0756292 -9.9379418 -21.7091644
## .pos
## -0.0570999
## [1] "max lambda < lambdaOpt:"
## (Intercept) .inp.fctrCC .inp.fctrGE .inp.fctrIBM .inp.fctrPG
## 172.44724646 -13.04655359 -69.90089659 -13.61490564 -23.59904481
## .pos
## -0.05898694
## [1] "myfit_mdl: train diagnostics complete: 1.742000 secs"
## [1] "myfit_mdl: predict complete: 1.900000 secs"
## id feats max.nTuningRuns
## 1 Max.cor.Y.rcv.1X1###glmnet .pos,.inp.fctr 0
## min.elapsedtime.everything min.elapsedtime.final max.R.sq.fit
## 1 0.656 0.011 0.4354461
## min.RMSE.fit max.Adj.R.sq.fit max.R.sq.OOB min.RMSE.OOB max.Adj.R.sq.OOB
## 1 42.0929 0.434267 -5.871796 146.8559 -5.886148
## [1] "myfit_mdl: exit: 1.905000 secs"if (glbMdlCheckRcv) {
# rcv_n_folds == 1 & rcv_n_repeats > 1 crashes
for (rcv_n_folds in seq(3, glb_rcv_n_folds + 2, 2))
for (rcv_n_repeats in seq(1, glb_rcv_n_repeats + 2, 2)) {
# Experiment specific code to avoid caret crash
# lcl_tune_models_df <- rbind(data.frame()
# ,data.frame(method = "glmnet", parameter = "alpha",
# vals = "0.100 0.325 0.550 0.775 1.000")
# ,data.frame(method = "glmnet", parameter = "lambda",
# vals = "9.342e-02")
# )
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst =
list(
id.prefix = paste0("Max.cor.Y.rcv.", rcv_n_folds, "X", rcv_n_repeats),
type = glb_model_type,
# tune.df = lcl_tune_models_df,
trainControl.method = "repeatedcv",
trainControl.number = rcv_n_folds,
trainControl.repeats = rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
train.method = "glmnet", train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize)),
indepVar = max_cor_y_x_vars, rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}
# Add parallel coordinates graph of glb_models_df[, glbMdlMetricsEval] to evaluate cv parameters
tmp_models_cols <- c("id", "max.nTuningRuns",
glbMdlMetricsEval[glbMdlMetricsEval %in% names(glb_models_df)],
grep("opt.", names(glb_models_df), fixed = TRUE, value = TRUE))
print(myplot_parcoord(obs_df = subset(glb_models_df,
grepl("Max.cor.Y.rcv.", id, fixed = TRUE),
select = -feats)[, tmp_models_cols],
id_var = "id"))
}
# Useful for stacking decisions
# fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
# paste0("fit.models_0_", "Max.cor.Y[rcv.1X1.cp.0|]"), major.inc = FALSE,
# label.minor = "rpart")
#
# ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
# id.prefix = "Max.cor.Y.rcv.1X1.cp.0", type = glb_model_type, trainControl.method = "none",
# train.method = "rpart",
# tune.df=data.frame(method="rpart", parameter="cp", min=0.0, max=0.0, by=0.1))),
# indepVar=max_cor_y_x_vars, rsp_var=glb_rsp_var,
# fit_df=glbObsFit, OOB_df=glbObsOOB)
#stop(here"); glb2Sav(); all.equal(glb_models_df, sav_models_df)
# if (glb_is_regression || glb_is_binomial) # For multinomials this model will be run next by default
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y",
type = glb_model_type, trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds,
trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "rpart")),
indepVar = max_cor_y_x_vars, rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: Max.cor.Y##rcv#rpart"
## [1] " indepVar: .pos,.inp.fctr"
## [1] "myfit_mdl: setup complete: 0.708000 secs"## Loading required package: rpart## Warning in nominalTrainWorkflow(x = x, y = y, wts = weights, info =
## trainInfo, : There were missing values in resampled performance measures.## Aggregating results
## Selecting tuning parameters
## Fitting cp = 0.0177 on full training set
## [1] "myfit_mdl: train complete: 2.360000 secs"## Warning in myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst
## = list(id.prefix = "Max.cor.Y", : model's bestTune found at an extreme of
## tuneGrid for parameter: cp## Loading required package: rpart.plot
## Call:
## rpart(formula = .outcome ~ ., control = list(minsplit = 20, minbucket = 7,
## cp = 0, maxcompete = 4, maxsurrogate = 5, usesurrogate = 2,
## surrogatestyle = 0, maxdepth = 30, xval = 0))
## n= 2400
##
## CP nsplit rel error
## 1 0.68121025 0 1.0000000
## 2 0.06636897 1 0.3187897
## 3 0.03265173 2 0.2524208
## 4 0.03109733 3 0.2197691
## 5 0.01766860 4 0.1886717
##
## Variable importance
## .pos .inp.fctrIBM .inp.fctrPG .inp.fctrCC .inp.fctrGE
## 89 7 1 1 1
##
## Node number 1: 2400 observations, complexity param=0.6812103
## mean=77.60114, MSE=3138.429
## left son=2 (2287 obs) right son=3 (113 obs)
## Primary splits:
## .pos < 113.5 to the right, improve=6.812103e-01, (0 missing)
## .inp.fctrIBM < 0.5 to the left, improve=3.551739e-01, (0 missing)
## .inp.fctrGE < 0.5 to the right, improve=2.666968e-02, (0 missing)
## .inp.fctrCC < 0.5 to the right, improve=2.459468e-02, (0 missing)
## .inp.fctrPG < 0.5 to the left, improve=8.512303e-07, (0 missing)
##
## Node number 2: 2287 observations, complexity param=0.06636897
## mean=67.32328, MSE=852.3751
## left son=4 (1903 obs) right son=5 (384 obs)
## Primary splits:
## .pos < 497.5 to the right, improve=0.25644350, (0 missing)
## .inp.fctrIBM < 0.5 to the left, improve=0.25262720, (0 missing)
## .inp.fctrPG < 0.5 to the left, improve=0.03358540, (0 missing)
## .inp.fctrGE < 0.5 to the right, improve=0.02004364, (0 missing)
## .inp.fctrCC < 0.5 to the right, improve=0.01657792, (0 missing)
## Surrogate splits:
## .inp.fctrIBM < 0.5 to the left, agree=0.993, adj=0.956, (0 split)
##
## Node number 3: 113 observations, complexity param=0.03265173
## mean=285.6142, MSE=3998.366
## left son=6 (69 obs) right son=7 (44 obs)
## Primary splits:
## .pos < 44.5 to the right, improve=0.544338, (0 missing)
##
## Node number 4: 1903 observations, complexity param=0.03109733
## mean=60.68191, MSE=602.5245
## left son=8 (871 obs) right son=9 (1032 obs)
## Primary splits:
## .pos < 1529.5 to the right, improve=0.2042834000, (0 missing)
## .inp.fctrPG < 0.5 to the left, improve=0.1622234000, (0 missing)
## .inp.fctrGE < 0.5 to the right, improve=0.0029852640, (0 missing)
## .inp.fctrCC < 0.5 to the right, improve=0.0002381228, (0 missing)
## Surrogate splits:
## .inp.fctrPG < 0.5 to the left, agree=0.710, adj=0.366, (0 split)
## .inp.fctrCC < 0.5 to the right, agree=0.701, adj=0.347, (0 split)
## .inp.fctrGE < 0.5 to the left, agree=0.701, adj=0.347, (0 split)
##
## Node number 5: 384 observations
## mean=100.2361, MSE=788.7282
##
## Node number 6: 69 observations
## mean=248.3598, MSE=1345.133
##
## Node number 7: 44 observations
## mean=344.0358, MSE=2569.565
##
## Node number 8: 871 observations
## mean=48.60559, MSE=304.1865
##
## Node number 9: 1032 observations
## mean=70.87423, MSE=627.3502
##
## n= 2400
##
## node), split, n, deviance, yval
## * denotes terminal node
##
## 1) root 2400 7532229.0 77.60114
## 2) .pos>=113.5 2287 1949382.0 67.32328
## 4) .pos>=497.5 1903 1146604.0 60.68191
## 8) .pos>=1529.5 871 264946.5 48.60559 *
## 9) .pos< 1529.5 1032 647425.4 70.87423 *
## 5) .pos< 497.5 384 302871.6 100.23610 *
## 3) .pos< 113.5 113 451815.3 285.61420
## 6) .pos>=44.5 69 92814.2 248.35980 *
## 7) .pos< 44.5 44 113060.9 344.03580 *
## [1] "myfit_mdl: train diagnostics complete: 3.089000 secs"
## [1] "myfit_mdl: predict complete: 3.138000 secs"
## id feats max.nTuningRuns
## 1 Max.cor.Y##rcv#rpart .pos,.inp.fctr 5
## min.elapsedtime.everything min.elapsedtime.final max.R.sq.fit
## 1 1.646 0.02 0.8113283
## min.RMSE.fit max.Adj.R.sq.fit max.R.sq.OOB min.RMSE.OOB max.Adj.R.sq.OOB
## 1 24.2999 NA -0.2678863 63.08067 NA
## max.Rsquared.fit min.RMSESD.fit max.RsquaredSD.fit
## 1 0.8083695 1.5931 0.03917691
## [1] "myfit_mdl: exit: 3.148000 secs"if ((length(glbFeatsDateTime) > 0) &&
(sum(grepl(paste(names(glbFeatsDateTime), "\\.day\\.minutes\\.poly\\.", sep = ""),
names(glbObsAll))) > 0)) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Max.cor.Y.Time.Poly"), major.inc = FALSE,
label.minor = "glmnet")
indepVars <- c(max_cor_y_x_vars,
grep(paste(names(glbFeatsDateTime), "\\.day\\.minutes\\.poly\\.", sep = ""),
names(glbObsAll), value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Time.Poly",
type = glb_model_type, trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}
if ((length(glbFeatsDateTime) > 0) &&
(sum(grepl(paste(names(glbFeatsDateTime), "\\.last[[:digit:]]", sep = ""),
names(glbObsAll))) > 0)) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Max.cor.Y.Time.Lag"), major.inc = FALSE,
label.minor = "glmnet")
indepVars <- c(max_cor_y_x_vars,
grep(paste(names(glbFeatsDateTime), "\\.last[[:digit:]]", sep = ""),
names(glbObsAll), value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Time.Lag",
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}## label step_major step_minor label_minor
## 2 fit.models_0_Max.cor.Y.rcv.*X* 1 1 glmnet
## 3 fit.models_0_Max.cor.Y.Time.Lag 1 2 glmnet
## bgn end elapsed
## 2 118.444 123.609 5.165
## 3 123.610 NA NA
## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: Max.cor.Y.Time.Lag##rcv#glmnet"
## [1] " indepVar: .pos,.inp.fctr,Date.last2.log1p,Date.last4.log1p,Date.last8.log1p,Date.last16.log1p,Date.last32.log1p"
## [1] "myfit_mdl: setup complete: 0.716000 secs"
## Aggregating results
## Selecting tuning parameters
## Fitting alpha = 1, lambda = 0.031 on full training set
## [1] "myfit_mdl: train complete: 3.087000 secs"## Warning in myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst
## = list(id.prefix = "Max.cor.Y.Time.Lag", : model's bestTune found at an
## extreme of tuneGrid for parameter: alpha## Warning in myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst
## = list(id.prefix = "Max.cor.Y.Time.Lag", : model's bestTune found at an
## extreme of tuneGrid for parameter: lambda
## Length Class Mode
## a0 82 -none- numeric
## beta 820 dgCMatrix S4
## df 82 -none- numeric
## dim 2 -none- numeric
## lambda 82 -none- numeric
## dev.ratio 82 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 10 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 1 -none- logical
## [1] "min lambda > lambdaOpt:"
## (Intercept) .inp.fctrCC .inp.fctrGE .pos
## 2098.61180122 27.61931367 -39.63407436 -0.09460833
## Date.last16.log1p Date.last2.log1p Date.last32.log1p Date.last4.log1p
## -89.45797902 -0.82554594 -41.58659723 -4.03296203
## Date.last8.log1p
## 13.33757292
## [1] "max lambda < lambdaOpt:"
## (Intercept) .inp.fctrCC .inp.fctrGE .pos
## 2095.87460765 27.73800452 -39.52922603 -0.09483527
## Date.last16.log1p Date.last2.log1p Date.last32.log1p Date.last4.log1p
## -89.97321520 -0.85098328 -41.02827399 -4.04835290
## Date.last8.log1p
## 13.49586361
## [1] "myfit_mdl: train diagnostics complete: 3.734000 secs"
## [1] "myfit_mdl: predict complete: 3.889000 secs"
## id
## 1 Max.cor.Y.Time.Lag##rcv#glmnet
## feats
## 1 .pos,.inp.fctr,Date.last2.log1p,Date.last4.log1p,Date.last8.log1p,Date.last16.log1p,Date.last32.log1p
## max.nTuningRuns min.elapsedtime.everything min.elapsedtime.final
## 1 25 2.363 0.008
## max.R.sq.fit min.RMSE.fit max.Adj.R.sq.fit max.R.sq.OOB min.RMSE.OOB
## 1 0.4456674 41.81473 0.4433471 -16.20049 232.3414
## max.Adj.R.sq.OOB max.Rsquared.fit min.RMSESD.fit max.RsquaredSD.fit
## 1 -16.27249 0.4436578 1.961742 0.0210011
## [1] "myfit_mdl: exit: 3.898000 secs"if (length(glbFeatsText) > 0) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Txt.*"), major.inc = FALSE,
label.minor = "glmnet")
indepVars <- c(max_cor_y_x_vars)
for (txtFeat in names(glbFeatsText))
indepVars <- union(indepVars,
grep(paste(str_to_upper(substr(txtFeat, 1, 1)), "\\.(?!([T|P]\\.))", sep = ""),
names(glbObsAll), perl = TRUE, value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Text.nonTP",
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
indepVars <- c(max_cor_y_x_vars)
for (txtFeat in names(glbFeatsText))
indepVars <- union(indepVars,
grep(paste(str_to_upper(substr(txtFeat, 1, 1)), "\\.T\\.", sep = ""),
names(glbObsAll), perl = TRUE, value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Text.onlyT",
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
indepVars <- c(max_cor_y_x_vars)
for (txtFeat in names(glbFeatsText))
indepVars <- union(indepVars,
grep(paste(str_to_upper(substr(txtFeat, 1, 1)), "\\.P\\.", sep = ""),
names(glbObsAll), perl = TRUE, value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Text.onlyP",
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}
# Interactions.High.cor.Y
if (length(int_feats <- setdiff(setdiff(unique(glb_feats_df$cor.high.X), NA),
subset(glb_feats_df, nzv)$id)) > 0) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Interact.High.cor.Y"), major.inc = FALSE,
label.minor = "glmnet")
ret_lst <- myfit_mdl(mdl_specs_lst=myinit_mdl_specs_lst(mdl_specs_lst=list(
id.prefix="Interact.High.cor.Y",
type=glb_model_type, trainControl.method="repeatedcv",
trainControl.number=glb_rcv_n_folds, trainControl.repeats=glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method="glmnet")),
indepVar=c(max_cor_y_x_vars, paste(max_cor_y_x_vars[1], int_feats, sep=":")),
rsp_var=glb_rsp_var,
fit_df=glbObsFit, OOB_df=glbObsOOB)
} ## label step_major step_minor label_minor
## 3 fit.models_0_Max.cor.Y.Time.Lag 1 2 glmnet
## 4 fit.models_0_Interact.High.cor.Y 1 3 glmnet
## bgn end elapsed
## 3 123.610 127.523 3.913
## 4 127.524 NA NA
## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: Interact.High.cor.Y##rcv#glmnet"
## [1] " indepVar: .pos,.inp.fctr,.pos:.pos,.pos:Date.last2.log1p,.pos:.inp.fctr,.pos:Date.month.fctr"
## [1] "myfit_mdl: setup complete: 0.693000 secs"
## Aggregating results
## Selecting tuning parameters
## Fitting alpha = 0.775, lambda = 0.031 on full training set
## [1] "myfit_mdl: train complete: 2.742000 secs"## Warning in myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst
## = list(id.prefix = "Interact.High.cor.Y", : model's bestTune found at an
## extreme of tuneGrid for parameter: lambda
## Length Class Mode
## a0 100 -none- numeric
## beta 2100 dgCMatrix S4
## df 100 -none- numeric
## dim 2 -none- numeric
## lambda 100 -none- numeric
## dev.ratio 100 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 21 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 1 -none- logical
## [1] "min lambda > lambdaOpt:"
## (Intercept) .inp.fctrCC .inp.fctrGE
## -9.762345e+00 1.832662e+02 9.656596e+01
## .inp.fctrIBM .inp.fctrPG .pos
## 2.542077e+02 1.121132e+02 2.636437e-02
## .inp.fctrCC:.pos .inp.fctrIBM:.pos .inp.fctrPG:.pos
## -9.382200e-02 -3.781724e-01 -4.684007e-02
## .pos:Date.last2.log1p .pos:Date.month.fctr02 .pos:Date.month.fctr03
## -4.366286e-03 4.024177e-04 4.235355e-04
## .pos:Date.month.fctr04 .pos:Date.month.fctr05 .pos:Date.month.fctr06
## 8.023870e-04 6.666666e-04 -6.779110e-05
## .pos:Date.month.fctr07 .pos:Date.month.fctr08 .pos:Date.month.fctr09
## -6.328364e-04 -4.887492e-04 -8.643801e-04
## .pos:Date.month.fctr10 .pos:Date.month.fctr11 .pos:Date.month.fctr12
## -1.105606e-03 -5.414138e-04 -5.782762e-06
## [1] "max lambda < lambdaOpt:"
## (Intercept) .inp.fctrCC .inp.fctrGE
## -1.781511e+01 1.928982e+02 1.048194e+02
## .inp.fctrIBM .inp.fctrPG .pos
## 2.623056e+02 1.208802e+02 3.011096e-02
## .inp.fctrCC:.pos .inp.fctrIBM:.pos .inp.fctrPG:.pos
## -9.847602e-02 -3.780618e-01 -5.114845e-02
## .pos:Date.last2.log1p .pos:Date.month.fctr02 .pos:Date.month.fctr03
## -4.636175e-03 3.809974e-04 3.999406e-04
## .pos:Date.month.fctr04 .pos:Date.month.fctr05 .pos:Date.month.fctr06
## 7.798091e-04 6.429269e-04 -1.026471e-04
## .pos:Date.month.fctr07 .pos:Date.month.fctr08 .pos:Date.month.fctr09
## -6.688349e-04 -5.247464e-04 -9.009481e-04
## .pos:Date.month.fctr10 .pos:Date.month.fctr11 .pos:Date.month.fctr12
## -1.143313e-03 -5.790881e-04 -4.460437e-05
## [1] "myfit_mdl: train diagnostics complete: 3.378000 secs"
## [1] "myfit_mdl: predict complete: 3.531000 secs"
## id
## 1 Interact.High.cor.Y##rcv#glmnet
## feats
## 1 .pos,.inp.fctr,.pos:.pos,.pos:Date.last2.log1p,.pos:.inp.fctr,.pos:Date.month.fctr
## max.nTuningRuns min.elapsedtime.everything min.elapsedtime.final
## 1 25 2.041 0.015
## max.R.sq.fit min.RMSE.fit max.Adj.R.sq.fit max.R.sq.OOB min.RMSE.OOB
## 1 0.6172344 34.88221 0.6138542 -45.45308 381.8241
## max.Adj.R.sq.OOB max.Rsquared.fit min.RMSESD.fit max.RsquaredSD.fit
## 1 -45.8633 0.612902 1.459778 0.03746229
## [1] "myfit_mdl: exit: 3.541000 secs"# Low.cor.X
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Low.cor.X"), major.inc = FALSE,
label.minor = "glmnet")## label step_major step_minor label_minor
## 4 fit.models_0_Interact.High.cor.Y 1 3 glmnet
## 5 fit.models_0_Low.cor.X 1 4 glmnet
## bgn end elapsed
## 4 127.524 131.075 3.551
## 5 131.075 NA NAindepVar <- mygetIndepVar(glb_feats_df)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Low.cor.X",
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVar, rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: Low.cor.X##rcv#glmnet"
## [1] " indepVar: .inp.fctr,Date.last2.log1p,Date.last32.log1p,Date.last4.log1p,Date.wkday.fctr,Date.wkend,.rnorm,Date.last8.log1p,Date.last16.log1p,Date.juliandate,Date.month.fctr,.pos,.pos.y,.rownames"
## [1] "myfit_mdl: setup complete: 0.707000 secs"
## Aggregating results
## Selecting tuning parameters
## Fitting alpha = 1, lambda = 0.144 on full training set
## [1] "myfit_mdl: train complete: 3.071000 secs"## Warning in myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst
## = list(id.prefix = "Low.cor.X", : model's bestTune found at an extreme of
## tuneGrid for parameter: alpha
## Length Class Mode
## a0 86 -none- numeric
## beta 2752 dgCMatrix S4
## df 86 -none- numeric
## dim 2 -none- numeric
## lambda 86 -none- numeric
## dev.ratio 86 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 32 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 1 -none- logical
## [1] "min lambda > lambdaOpt:"
## (Intercept) .inp.fctrCC .inp.fctrGE .pos
## 1.798626e+03 2.238909e+01 -4.421574e+01 -7.255471e-02
## .rnorm .rownames Date.juliandate Date.last16.log1p
## 5.052143e-01 -1.215360e-02 -6.392147e-03 -1.013606e+02
## Date.last2.log1p Date.last4.log1p Date.month.fctr02 Date.month.fctr03
## -1.002126e+00 -3.358519e+00 3.029397e+00 -6.075795e-01
## Date.month.fctr05 Date.month.fctr06 Date.month.fctr07 Date.month.fctr08
## 1.717577e+00 -6.067895e-01 -1.042922e+00 -4.149733e-01
## Date.month.fctr10 Date.month.fctr12 Date.wkday.fctr4 Date.wkday.fctr6
## -1.120237e+00 6.543330e-01 1.070070e+00 3.014252e-01
## [1] "max lambda < lambdaOpt:"
## (Intercept) .inp.fctrCC .inp.fctrGE .pos
## 1.841415e+03 2.294225e+01 -4.373128e+01 -7.327536e-02
## .rnorm .rownames Date.juliandate Date.last16.log1p
## 5.163244e-01 -1.248840e-02 -6.428555e-03 -1.039757e+02
## Date.last2.log1p Date.last4.log1p Date.month.fctr02 Date.month.fctr03
## -1.069648e+00 -3.430272e+00 3.092951e+00 -7.588476e-01
## Date.month.fctr05 Date.month.fctr06 Date.month.fctr07 Date.month.fctr08
## 1.741870e+00 -6.652235e-01 -1.102323e+00 -4.689666e-01
## Date.month.fctr10 Date.month.fctr12 Date.wkday.fctr4 Date.wkday.fctr6
## -1.172213e+00 6.976209e-01 1.113995e+00 3.503962e-01
## [1] "myfit_mdl: train diagnostics complete: 3.686000 secs"
## [1] "myfit_mdl: predict complete: 3.858000 secs"
## id
## 1 Low.cor.X##rcv#glmnet
## feats
## 1 .inp.fctr,Date.last2.log1p,Date.last32.log1p,Date.last4.log1p,Date.wkday.fctr,Date.wkend,.rnorm,Date.last8.log1p,Date.last16.log1p,Date.juliandate,Date.month.fctr,.pos,.pos.y,.rownames
## max.nTuningRuns min.elapsedtime.everything min.elapsedtime.final
## 1 25 2.351 0.012
## max.R.sq.fit min.RMSE.fit max.Adj.R.sq.fit max.R.sq.OOB min.RMSE.OOB
## 1 0.446 42.07752 0.4385103 -3.099567 113.4293
## max.Adj.R.sq.OOB max.Rsquared.fit min.RMSESD.fit max.RsquaredSD.fit
## 1 -3.15499 0.4367487 2.060214 0.01913324
## [1] "myfit_mdl: exit: 3.867000 secs"fit.models_0_chunk_df <-
myadd_chunk(fit.models_0_chunk_df, "fit.models_0_end", major.inc = FALSE,
label.minor = "teardown")## label step_major step_minor label_minor bgn end
## 5 fit.models_0_Low.cor.X 1 4 glmnet 131.075 134.961
## 6 fit.models_0_end 1 5 teardown 134.962 NA
## elapsed
## 5 3.886
## 6 NArm(ret_lst)
glb_chunks_df <- myadd_chunk(glb_chunks_df, "fit.models", major.inc = FALSE)## label step_major step_minor label_minor bgn end elapsed
## 16 fit.models 8 0 0 117.848 134.981 17.133
## 17 fit.models 8 1 1 134.981 NA NAfit.models_1_chunk_df <- myadd_chunk(NULL, "fit.models_1_bgn", label.minor = "setup")## label step_major step_minor label_minor bgn end elapsed
## 1 fit.models_1_bgn 1 0 setup 136.462 NA NA# refactor code for outliers / ensure all model runs exclude outliers in this chunk ???
#stop(here"); glb2Sav(); all.equal(glb_models_df, sav_models_df)
topindep_var <- NULL; interact_vars <- NULL;
for (mdl_id_pfx in names(glbMdlFamilies)) {
fit.models_1_chunk_df <-
myadd_chunk(fit.models_1_chunk_df, paste0("fit.models_1_", mdl_id_pfx),
major.inc = FALSE, label.minor = "setup")
indepVar <- NULL;
if (grepl("\\.Interact", mdl_id_pfx)) {
if (is.null(topindep_var) && is.null(interact_vars)) {
# select best glmnet model upto now
dsp_models_df <- orderBy(model_sel_frmla <- get_model_sel_frmla(),
glb_models_df)
dsp_models_df <- subset(dsp_models_df,
grepl(".glmnet", id, fixed = TRUE))
bst_mdl_id <- dsp_models_df$id[1]
mdl_id_pfx <-
paste(c(head(unlist(strsplit(bst_mdl_id, "[.]")), -1), "Interact"),
collapse=".")
# select important features
if (is.null(bst_featsimp_df <-
myget_feats_importance(glb_models_lst[[bst_mdl_id]]))) {
warning("Base model for RFE.Interact: ", bst_mdl_id,
" has no important features")
next
}
topindep_ix <- 1
while (is.null(topindep_var) && (topindep_ix <= nrow(bst_featsimp_df))) {
topindep_var <- row.names(bst_featsimp_df)[topindep_ix]
if (grepl(".fctr", topindep_var, fixed=TRUE))
topindep_var <-
paste0(unlist(strsplit(topindep_var, ".fctr"))[1], ".fctr")
if (topindep_var %in% names(glbFeatsInteractionOnly)) {
topindep_var <- NULL; topindep_ix <- topindep_ix + 1
} else break
}
# select features with importance > max(10, importance of .rnorm) & is not highest
# combine factor dummy features to just the factor feature
if (length(pos_rnorm <-
grep(".rnorm", row.names(bst_featsimp_df), fixed=TRUE)) > 0)
imp_rnorm <- bst_featsimp_df[pos_rnorm, 1] else
imp_rnorm <- NA
imp_cutoff <- max(10, imp_rnorm, na.rm=TRUE)
interact_vars <-
tail(row.names(subset(bst_featsimp_df,
imp > imp_cutoff)), -1)
if (length(interact_vars) > 0) {
interact_vars <-
myadjustInteractionFeats(glb_feats_df, myextract_actual_feats(interact_vars))
interact_vars <-
interact_vars[!grepl(topindep_var, interact_vars, fixed=TRUE)]
}
### bid0_sp only
# interact_vars <- c(
# "biddable", "D.ratio.sum.TfIdf.wrds.n", "D.TfIdf.sum.stem.stop.Ratio", "D.sum.TfIdf",
# "D.TfIdf.sum.post.stop", "D.TfIdf.sum.post.stem", "D.ratio.wrds.stop.n.wrds.n", "D.chrs.uppr.n.log",
# "D.chrs.n.log", "color.fctr"
# # , "condition.fctr", "prdl.my.descr.fctr"
# )
# interact_vars <- setdiff(interact_vars, c("startprice.dgt2.is9", "color.fctr"))
###
indepVar <- myextract_actual_feats(row.names(bst_featsimp_df))
indepVar <- setdiff(indepVar, topindep_var)
if (length(interact_vars) > 0) {
indepVar <-
setdiff(indepVar, myextract_actual_feats(interact_vars))
indepVar <- c(indepVar,
paste(topindep_var, setdiff(interact_vars, topindep_var),
sep = "*"))
} else indepVar <- union(indepVar, topindep_var)
}
}
if (is.null(indepVar))
indepVar <- glb_mdl_feats_lst[[mdl_id_pfx]]
if (is.null(indepVar) && grepl("RFE\\.", mdl_id_pfx))
indepVar <- myextract_actual_feats(predictors(rfe_fit_results))
if (is.null(indepVar))
indepVar <- mygetIndepVar(glb_feats_df)
if ((length(indepVar) == 1) && (grepl("^%<d-%", indepVar))) {
indepVar <-
eval(parse(text = str_trim(unlist(strsplit(indepVar, "%<d-%"))[2])))
}
indepVar <- myadjustInteractionFeats(glb_feats_df, indepVar)
if (grepl("\\.Interact", mdl_id_pfx)) {
# if (method != tail(unlist(strsplit(bst_mdl_id, "[.]")), 1)) next
if (is.null(glbMdlFamilies[[mdl_id_pfx]])) {
if (!is.null(glbMdlFamilies[["Best.Interact"]]))
glbMdlFamilies[[mdl_id_pfx]] <-
glbMdlFamilies[["Best.Interact"]]
}
}
if (!is.null(glbObsFitOutliers[[mdl_id_pfx]])) {
fitobs_df <- glbObsFit[!(glbObsFit[, glbFeatsId] %in%
glbObsFitOutliers[[mdl_id_pfx]]), ]
print(sprintf("Outliers removed: %d", nrow(glbObsFit) - nrow(fitobs_df)))
print(setdiff(glbObsFit[, glbFeatsId], fitobs_df[, glbFeatsId]))
} else fitobs_df <- glbObsFit
if (is.null(glbMdlFamilies[[mdl_id_pfx]]))
mdl_methods <- glbMdlMethods else
mdl_methods <- glbMdlFamilies[[mdl_id_pfx]]
for (method in mdl_methods) {
if (method %in% c("rpart", "rf")) {
# rpart: fubar's the tree
# rf: skip the scenario w/ .rnorm for speed
indepVar <- setdiff(indepVar, c(".rnorm"))
#mdl_id <- paste0(mdl_id_pfx, ".no.rnorm")
}
fit.models_1_chunk_df <- myadd_chunk(fit.models_1_chunk_df,
paste0("fit.models_1_", mdl_id_pfx), major.inc = FALSE,
label.minor = method)
ret_lst <-
myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = mdl_id_pfx,
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv", # or "none" if nominalWorkflow is crashing
trainControl.number = glb_rcv_n_folds,
trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = method)),
indepVar = indepVar, rsp_var = glb_rsp_var,
fit_df = fitobs_df, OOB_df = glbObsOOB)
# ntv_mdl <- glmnet(x = as.matrix(
# fitobs_df[, indepVar]),
# y = as.factor(as.character(
# fitobs_df[, glb_rsp_var])),
# family = "multinomial")
# bgn = 1; end = 100;
# ntv_mdl <- glmnet(x = as.matrix(
# subset(fitobs_df, pop.fctr != "crypto")[bgn:end, indepVar]),
# y = as.factor(as.character(
# subset(fitobs_df, pop.fctr != "crypto")[bgn:end, glb_rsp_var])),
# family = "multinomial")
}
}## label step_major step_minor label_minor bgn end
## 1 fit.models_1_bgn 1 0 setup 136.462 136.473
## 2 fit.models_1_All.X 1 1 setup 136.474 NA
## elapsed
## 1 0.011
## 2 NA
## label step_major step_minor label_minor bgn end
## 2 fit.models_1_All.X 1 1 setup 136.474 136.481
## 3 fit.models_1_All.X 1 2 glmnet 136.481 NA
## elapsed
## 2 0.007
## 3 NA
## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: All.X##rcv#glmnet"
## [1] " indepVar: .inp.fctr,Date.last2.log1p,Date.last32.log1p,Date.last4.log1p,Date.wkday.fctr,Date.wkend,.rnorm,Date.last8.log1p,Date.last16.log1p,Date.juliandate,Date.month.fctr,.pos,.pos.y,.rownames"
## [1] "myfit_mdl: setup complete: 0.697000 secs"
## Aggregating results
## Selecting tuning parameters
## Fitting alpha = 1, lambda = 0.144 on full training set
## [1] "myfit_mdl: train complete: 2.755000 secs"## Warning in myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst
## = list(id.prefix = mdl_id_pfx, : model's bestTune found at an extreme of
## tuneGrid for parameter: alpha
## Length Class Mode
## a0 86 -none- numeric
## beta 2752 dgCMatrix S4
## df 86 -none- numeric
## dim 2 -none- numeric
## lambda 86 -none- numeric
## dev.ratio 86 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 32 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 1 -none- logical
## [1] "min lambda > lambdaOpt:"
## (Intercept) .inp.fctrCC .inp.fctrGE .pos
## 1.798626e+03 2.238909e+01 -4.421574e+01 -7.255471e-02
## .rnorm .rownames Date.juliandate Date.last16.log1p
## 5.052143e-01 -1.215360e-02 -6.392147e-03 -1.013606e+02
## Date.last2.log1p Date.last4.log1p Date.month.fctr02 Date.month.fctr03
## -1.002126e+00 -3.358519e+00 3.029397e+00 -6.075795e-01
## Date.month.fctr05 Date.month.fctr06 Date.month.fctr07 Date.month.fctr08
## 1.717577e+00 -6.067895e-01 -1.042922e+00 -4.149733e-01
## Date.month.fctr10 Date.month.fctr12 Date.wkday.fctr4 Date.wkday.fctr6
## -1.120237e+00 6.543330e-01 1.070070e+00 3.014252e-01
## [1] "max lambda < lambdaOpt:"
## (Intercept) .inp.fctrCC .inp.fctrGE .pos
## 1.841415e+03 2.294225e+01 -4.373128e+01 -7.327536e-02
## .rnorm .rownames Date.juliandate Date.last16.log1p
## 5.163244e-01 -1.248840e-02 -6.428555e-03 -1.039757e+02
## Date.last2.log1p Date.last4.log1p Date.month.fctr02 Date.month.fctr03
## -1.069648e+00 -3.430272e+00 3.092951e+00 -7.588476e-01
## Date.month.fctr05 Date.month.fctr06 Date.month.fctr07 Date.month.fctr08
## 1.741870e+00 -6.652235e-01 -1.102323e+00 -4.689666e-01
## Date.month.fctr10 Date.month.fctr12 Date.wkday.fctr4 Date.wkday.fctr6
## -1.172213e+00 6.976209e-01 1.113995e+00 3.503962e-01
## [1] "myfit_mdl: train diagnostics complete: 3.459000 secs"
## [1] "myfit_mdl: predict complete: 3.633000 secs"
## id
## 1 All.X##rcv#glmnet
## feats
## 1 .inp.fctr,Date.last2.log1p,Date.last32.log1p,Date.last4.log1p,Date.wkday.fctr,Date.wkend,.rnorm,Date.last8.log1p,Date.last16.log1p,Date.juliandate,Date.month.fctr,.pos,.pos.y,.rownames
## max.nTuningRuns min.elapsedtime.everything min.elapsedtime.final
## 1 25 2.045 0.012
## max.R.sq.fit min.RMSE.fit max.Adj.R.sq.fit max.R.sq.OOB min.RMSE.OOB
## 1 0.446 42.07752 0.4385103 -3.099567 113.4293
## max.Adj.R.sq.OOB max.Rsquared.fit min.RMSESD.fit max.RsquaredSD.fit
## 1 -3.15499 0.4367487 2.060214 0.01913324
## [1] "myfit_mdl: exit: 3.643000 secs"
## label step_major step_minor label_minor bgn end
## 3 fit.models_1_All.X 1 2 glmnet 136.481 140.129
## 4 fit.models_1_All.X 1 3 glm 140.130 NA
## elapsed
## 3 3.648
## 4 NA
## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: All.X##rcv#glm"
## [1] " indepVar: .inp.fctr,Date.last2.log1p,Date.last32.log1p,Date.last4.log1p,Date.wkday.fctr,Date.wkend,.rnorm,Date.last8.log1p,Date.last16.log1p,Date.juliandate,Date.month.fctr,.pos,.pos.y,.rownames"
## [1] "myfit_mdl: setup complete: 0.710000 secs"
## + Fold1.Rep1: parameter=none## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## - Fold1.Rep1: parameter=none
## + Fold2.Rep1: parameter=none## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## - Fold2.Rep1: parameter=none
## + Fold3.Rep1: parameter=none## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## - Fold3.Rep1: parameter=none
## + Fold1.Rep2: parameter=none## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## - Fold1.Rep2: parameter=none
## + Fold2.Rep2: parameter=none## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## - Fold2.Rep2: parameter=none
## + Fold3.Rep2: parameter=none## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## - Fold3.Rep2: parameter=none
## + Fold1.Rep3: parameter=none## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## - Fold1.Rep3: parameter=none
## + Fold2.Rep3: parameter=none## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## - Fold2.Rep3: parameter=none
## + Fold3.Rep3: parameter=none## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading
## - Fold3.Rep3: parameter=none
## Aggregating results
## Fitting final model on full training set
## [1] "myfit_mdl: train complete: 2.118000 secs"
##
## Call:
## NULL
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -111.354 -21.650 -3.038 12.678 273.399
##
## Coefficients: (3 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.757e+03 4.371e+03 1.546 0.1223
## .inp.fctrCC -4.145e+02 1.241e+03 -0.334 0.7384
## .inp.fctrGE 3.584e+02 1.269e+03 0.282 0.7777
## .inp.fctrIBM 3.970e+02 1.269e+03 0.313 0.7544
## .inp.fctrPG -4.432e+02 1.241e+03 -0.357 0.7210
## .pos -9.681e-02 6.185e-03 -15.653 <2e-16 ***
## .pos.y NA NA NA NA
## .rnorm 6.231e-01 8.369e-01 0.744 0.4567
## .rownames NA NA NA NA
## Date.juliandate 3.554e+00 2.358e+00 1.507 0.1319
## Date.last16.log1p -6.483e+02 2.981e+02 -2.175 0.0297 *
## Date.last2.log1p -6.160e+01 6.990e+01 -0.881 0.3783
## Date.last32.log1p 1.528e+02 2.112e+02 0.723 0.4695
## Date.last4.log1p 2.580e+01 8.397e+01 0.307 0.7587
## Date.last8.log1p 7.455e+01 2.147e+02 0.347 0.7285
## Date.month.fctr02 -9.968e+01 7.235e+01 -1.378 0.1684
## Date.month.fctr03 -2.192e+02 1.447e+02 -1.515 0.1299
## Date.month.fctr04 -3.359e+02 2.151e+02 -1.561 0.1186
## Date.month.fctr05 -4.207e+02 2.852e+02 -1.475 0.1404
## Date.month.fctr06 -5.396e+02 3.569e+02 -1.512 0.1307
## Date.month.fctr07 -6.440e+02 4.283e+02 -1.504 0.1328
## Date.month.fctr08 -7.572e+02 5.004e+02 -1.513 0.1304
## Date.month.fctr09 -8.579e+02 5.725e+02 -1.498 0.1341
## Date.month.fctr10 -9.726e+02 6.449e+02 -1.508 0.1317
## Date.month.fctr11 -1.084e+03 7.172e+02 -1.512 0.1307
## Date.month.fctr12 -1.186e+03 7.889e+02 -1.503 0.1330
## Date.wkday.fctr1 1.525e-01 3.210e+00 0.048 0.9621
## Date.wkday.fctr2 3.328e-01 3.199e+00 0.104 0.9172
## Date.wkday.fctr3 3.642e-01 3.208e+00 0.114 0.9096
## Date.wkday.fctr4 1.856e+00 3.188e+00 0.582 0.5605
## Date.wkday.fctr5 6.916e-01 3.220e+00 0.215 0.8299
## Date.wkday.fctr6 1.276e+00 3.201e+00 0.399 0.6902
## Date.wkend NA NA NA NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 1752.843)
##
## Null deviance: 7532229 on 2399 degrees of freedom
## Residual deviance: 4154237 on 2370 degrees of freedom
## AIC: 24768
##
## Number of Fisher Scoring iterations: 2
##
## [1] "myfit_mdl: train diagnostics complete: 3.104000 secs"## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading## Warning in predict.lm(object, newdata, se.fit, scale = 1, type =
## ifelse(type == : prediction from a rank-deficient fit may be misleading
## [1] "myfit_mdl: predict complete: 3.234000 secs"
## id
## 1 All.X##rcv#glm
## feats
## 1 .inp.fctr,Date.last2.log1p,Date.last32.log1p,Date.last4.log1p,Date.wkday.fctr,Date.wkend,.rnorm,Date.last8.log1p,Date.last16.log1p,Date.juliandate,Date.month.fctr,.pos,.pos.y,.rownames
## max.nTuningRuns min.elapsedtime.everything min.elapsedtime.final
## 1 1 1.395 0.034
## max.R.sq.fit min.RMSE.fit min.aic.fit max.Adj.R.sq.fit max.R.sq.OOB
## 1 0.4484718 42.20301 24768.3 0.4417231 -188.8953
## min.RMSE.OOB max.Adj.R.sq.OOB max.Rsquared.fit min.RMSESD.fit
## 1 771.9928 -191.2189 0.4337656 2.014089
## max.RsquaredSD.fit
## 1 0.01975136
## [1] "myfit_mdl: exit: 3.243000 secs"# Check if other preProcess methods improve model performance
fit.models_1_chunk_df <-
myadd_chunk(fit.models_1_chunk_df, "fit.models_1_preProc", major.inc = FALSE,
label.minor = "preProc")## label step_major step_minor label_minor bgn end
## 4 fit.models_1_All.X 1 3 glm 140.130 143.383
## 5 fit.models_1_preProc 1 4 preProc 143.384 NA
## elapsed
## 4 3.253
## 5 NAmdl_id <- orderBy(get_model_sel_frmla(), glb_models_df)[1, "id"]
indepVar <- trim(unlist(strsplit(glb_models_df[glb_models_df$id == mdl_id,
"feats"], "[,]")))
method <- tail(unlist(strsplit(mdl_id, "[.]")), 1)
mdl_id_pfx <- paste0(head(unlist(strsplit(mdl_id, "[.]")), -1), collapse = ".")
if (!is.null(glbObsFitOutliers[[mdl_id_pfx]])) {
fitobs_df <- glbObsFit[!(glbObsFit[, glbFeatsId] %in%
glbObsFitOutliers[[mdl_id_pfx]]), ]
print(sprintf("Outliers removed: %d", nrow(glbObsFit) - nrow(fitobs_df)))
print(setdiff(glbObsFit[, glbFeatsId], fitobs_df[, glbFeatsId]))
} else fitobs_df <- glbObsFit
for (prePr in glb_preproc_methods) {
# The operations are applied in this order:
# Box-Cox/Yeo-Johnson transformation, centering, scaling, range, imputation, PCA, ICA then spatial sign.
ret_lst <- myfit_mdl(mdl_specs_lst=myinit_mdl_specs_lst(mdl_specs_lst=list(
id.prefix=mdl_id_pfx,
type=glb_model_type, tune.df=glbMdlTuneParams,
trainControl.method="repeatedcv",
trainControl.number=glb_rcv_n_folds,
trainControl.repeats=glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method=method, train.preProcess=prePr)),
indepVar=indepVar, rsp_var=glb_rsp_var,
fit_df=fitobs_df, OOB_df=glbObsOOB)
}
# If (All|RFE).X.glm is less accurate than Low.Cor.X.glm
# check NA coefficients & filter appropriate terms in indepVar
# if (method == "glm") {
# orig_glm <- glb_models_lst[[paste0(mdl_id, ".", model_method)]]$finalModel
# orig_glm <- glb_models_lst[["All.X.glm"]]$finalModel; print(summary(orig_glm))
# orig_glm <- glb_models_lst[["RFE.X.glm"]]$finalModel; print(summary(orig_glm))
# require(car)
# vif_orig_glm <- vif(orig_glm); print(vif_orig_glm)
# # if vif errors out with "there are aliased coefficients in the model"
# alias_orig_glm <- alias(orig_glm); alias_complete_orig_glm <- (alias_orig_glm$Complete > 0); alias_complete_orig_glm <- alias_complete_orig_glm[rowSums(alias_complete_orig_glm) > 0, colSums(alias_complete_orig_glm) > 0]; print(alias_complete_orig_glm)
# print(vif_orig_glm[!is.na(vif_orig_glm) & (vif_orig_glm == Inf)])
# print(which.max(vif_orig_glm))
# print(sort(vif_orig_glm[vif_orig_glm >= 1.0e+03], decreasing=TRUE))
# glbObsFit[c(1143, 3637, 3953, 4105), c("UniqueID", "Popular", "H.P.quandary", "Headline")]
# glb_feats_df[glb_feats_df$id %in% grep("[HSA]\\.chrs.n.log", glb_feats_df$id, value=TRUE) | glb_feats_df$cor.high.X %in% grep("[HSA]\\.chrs.n.log", glb_feats_df$id, value=TRUE), ]
# all.equal(glbObsAll$S.chrs.uppr.n.log, glbObsAll$A.chrs.uppr.n.log)
# cor(glbObsAll$S.T.herald, glbObsAll$S.T.tribun)
# mydspObs(Abstract.contains="[Dd]iar", cols=("Abstract"), all=TRUE)
# subset(glb_feats_df, cor.y.abs <= glb_feats_df[glb_feats_df$id == ".rnorm", "cor.y.abs"])
# corxx_mtrx <- cor(data.matrix(glbObsAll[, setdiff(names(glbObsAll), myfind_chr_cols_df(glbObsAll))]), use="pairwise.complete.obs"); abs_corxx_mtrx <- abs(corxx_mtrx); diag(abs_corxx_mtrx) <- 0
# which.max(abs_corxx_mtrx["S.T.tribun", ])
# abs_corxx_mtrx["A.npnct08.log", "S.npnct08.log"]
# step_glm <- step(orig_glm)
# }
# Since caret does not optimize rpart well
# if (method == "rpart")
# ret_lst <- myfit_mdl(mdl_id=paste0(mdl_id_pfx, ".cp.0"), model_method=method,
# indepVar=indepVar,
# model_type=glb_model_type,
# rsp_var=glb_rsp_var,
# fit_df=glbObsFit, OOB_df=glbObsOOB,
# n_cv_folds=0, tune_models_df=data.frame(parameter="cp", min=0.0, max=0.0, by=0.1))
# User specified
# Ensure at least 2 vars in each regression; else varImp crashes
# sav_models_lst <- glb_models_lst; sav_models_df <- glb_models_df; sav_featsimp_df <- glb_featsimp_df; all.equal(sav_featsimp_df, glb_featsimp_df)
# glb_models_lst <- sav_models_lst; glb_models_df <- sav_models_df; glm_featsimp_df <- sav_featsimp_df
# easier to exclude features
# require(gdata) # needed for trim
# mdl_id <- "";
# indepVar <- head(subset(glb_models_df, grepl("All\\.X\\.", mdl_id), select=feats)
# , 1)[, "feats"]
# indepVar <- trim(unlist(strsplit(indepVar, "[,]")))
# indepVar <- setdiff(indepVar, ".rnorm")
# easier to include features
#stop(here"); sav_models_df <- glb_models_df; glb_models_df <- sav_models_df
# !_sp
# mdl_id <- "csm"; indepVar <- c(NULL
# ,"prdline.my.fctr", "prdline.my.fctr:.clusterid.fctr"
# ,"prdline.my.fctr*biddable"
# #,"prdline.my.fctr*startprice.log"
# #,"prdline.my.fctr*startprice.diff"
# ,"prdline.my.fctr*condition.fctr"
# ,"prdline.my.fctr*D.terms.post.stop.n"
# #,"prdline.my.fctr*D.terms.post.stem.n"
# ,"prdline.my.fctr*cellular.fctr"
# # ,"<feat1>:<feat2>"
# )
# for (method in glbMdlMethods) {
# ret_lst <- myfit_mdl(mdl_id=mdl_id, model_method=method,
# indepVar=indepVar,
# model_type=glb_model_type,
# rsp_var=glb_rsp_var,
# fit_df=glbObsFit, OOB_df=glbObsOOB,
# n_cv_folds=glb_rcv_n_folds, tune_models_df=glbMdlTuneParams)
# csm_mdl_id <- paste0(mdl_id, ".", method)
# csm_featsimp_df <- myget_feats_importance(glb_models_lst[[paste0(mdl_id, ".",
# method)]]); print(head(csm_featsimp_df))
# }
###
# Ntv.1.lm <- lm(reformulate(indepVar, glb_rsp_var), glbObsTrn); print(summary(Ntv.1.lm))
#glb_models_df[, "max.Accuracy.OOB", FALSE]
#varImp(glb_models_lst[["Low.cor.X.glm"]])
#orderBy(~ -Overall, varImp(glb_models_lst[["All.X.2.glm"]])$imp)
#orderBy(~ -Overall, varImp(glb_models_lst[["All.X.3.glm"]])$imp)
#glb_feats_df[grepl("npnct28", glb_feats_df$id), ]
# User specified bivariate models
# indepVar_lst <- list()
# for (feat in setdiff(names(glbObsFit),
# union(glb_rsp_var, glbFeatsExclude)))
# indepVar_lst[["feat"]] <- feat
# User specified combinatorial models
# indepVar_lst <- list()
# combn_mtrx <- combn(c("<feat1_name>", "<feat2_name>", "<featn_name>"),
# <num_feats_to_choose>)
# for (combn_ix in 1:ncol(combn_mtrx))
# #print(combn_mtrx[, combn_ix])
# indepVar_lst[[combn_ix]] <- combn_mtrx[, combn_ix]
# template for myfit_mdl
# rf is hard-coded in caret to recognize only Accuracy / Kappa evaluation metrics
# only for OOB in trainControl ?
# ret_lst <- myfit_mdl_fn(mdl_id=paste0(mdl_id_pfx, ""), model_method=method,
# indepVar=indepVar,
# rsp_var=glb_rsp_var,
# fit_df=glbObsFit, OOB_df=glbObsOOB,
# n_cv_folds=glb_rcv_n_folds, tune_models_df=glbMdlTuneParams,
# model_loss_mtrx=glbMdlMetric_terms,
# model_summaryFunction=glbMdlMetricSummaryFn,
# model_metric=glbMdlMetricSummary,
# model_metric_maximize=glbMdlMetricMaximize)
# Simplify a model
# fit_df <- glbObsFit; glb_mdl <- step(<complex>_mdl)
# Non-caret models
# rpart_area_mdl <- rpart(reformulate("Area", response=glb_rsp_var),
# data=glbObsFit, #method="class",
# control=rpart.control(cp=0.12),
# parms=list(loss=glbMdlMetric_terms))
# print("rpart_sel_wlm_mdl"); prp(rpart_sel_wlm_mdl)
#
print(glb_models_df)## id
## Max.cor.Y.rcv.1X1###glmnet Max.cor.Y.rcv.1X1###glmnet
## Max.cor.Y##rcv#rpart Max.cor.Y##rcv#rpart
## Max.cor.Y.Time.Lag##rcv#glmnet Max.cor.Y.Time.Lag##rcv#glmnet
## Interact.High.cor.Y##rcv#glmnet Interact.High.cor.Y##rcv#glmnet
## Low.cor.X##rcv#glmnet Low.cor.X##rcv#glmnet
## All.X##rcv#glmnet All.X##rcv#glmnet
## All.X##rcv#glm All.X##rcv#glm
## feats
## Max.cor.Y.rcv.1X1###glmnet .pos,.inp.fctr
## Max.cor.Y##rcv#rpart .pos,.inp.fctr
## Max.cor.Y.Time.Lag##rcv#glmnet .pos,.inp.fctr,Date.last2.log1p,Date.last4.log1p,Date.last8.log1p,Date.last16.log1p,Date.last32.log1p
## Interact.High.cor.Y##rcv#glmnet .pos,.inp.fctr,.pos:.pos,.pos:Date.last2.log1p,.pos:.inp.fctr,.pos:Date.month.fctr
## Low.cor.X##rcv#glmnet .inp.fctr,Date.last2.log1p,Date.last32.log1p,Date.last4.log1p,Date.wkday.fctr,Date.wkend,.rnorm,Date.last8.log1p,Date.last16.log1p,Date.juliandate,Date.month.fctr,.pos,.pos.y,.rownames
## All.X##rcv#glmnet .inp.fctr,Date.last2.log1p,Date.last32.log1p,Date.last4.log1p,Date.wkday.fctr,Date.wkend,.rnorm,Date.last8.log1p,Date.last16.log1p,Date.juliandate,Date.month.fctr,.pos,.pos.y,.rownames
## All.X##rcv#glm .inp.fctr,Date.last2.log1p,Date.last32.log1p,Date.last4.log1p,Date.wkday.fctr,Date.wkend,.rnorm,Date.last8.log1p,Date.last16.log1p,Date.juliandate,Date.month.fctr,.pos,.pos.y,.rownames
## max.nTuningRuns min.elapsedtime.everything
## Max.cor.Y.rcv.1X1###glmnet 0 0.656
## Max.cor.Y##rcv#rpart 5 1.646
## Max.cor.Y.Time.Lag##rcv#glmnet 25 2.363
## Interact.High.cor.Y##rcv#glmnet 25 2.041
## Low.cor.X##rcv#glmnet 25 2.351
## All.X##rcv#glmnet 25 2.045
## All.X##rcv#glm 1 1.395
## min.elapsedtime.final max.R.sq.fit
## Max.cor.Y.rcv.1X1###glmnet 0.011 0.4354461
## Max.cor.Y##rcv#rpart 0.020 0.8113283
## Max.cor.Y.Time.Lag##rcv#glmnet 0.008 0.4456674
## Interact.High.cor.Y##rcv#glmnet 0.015 0.6172344
## Low.cor.X##rcv#glmnet 0.012 0.4460000
## All.X##rcv#glmnet 0.012 0.4460000
## All.X##rcv#glm 0.034 0.4484718
## min.RMSE.fit max.Adj.R.sq.fit max.R.sq.OOB
## Max.cor.Y.rcv.1X1###glmnet 42.09290 0.4342670 -5.8717963
## Max.cor.Y##rcv#rpart 24.29990 NA -0.2678863
## Max.cor.Y.Time.Lag##rcv#glmnet 41.81473 0.4433471 -16.2004933
## Interact.High.cor.Y##rcv#glmnet 34.88221 0.6138542 -45.4530763
## Low.cor.X##rcv#glmnet 42.07752 0.4385103 -3.0995666
## All.X##rcv#glmnet 42.07752 0.4385103 -3.0995666
## All.X##rcv#glm 42.20301 0.4417231 -188.8953069
## min.RMSE.OOB max.Adj.R.sq.OOB
## Max.cor.Y.rcv.1X1###glmnet 146.85585 -5.886148
## Max.cor.Y##rcv#rpart 63.08067 NA
## Max.cor.Y.Time.Lag##rcv#glmnet 232.34139 -16.272492
## Interact.High.cor.Y##rcv#glmnet 381.82413 -45.863301
## Low.cor.X##rcv#glmnet 113.42926 -3.154990
## All.X##rcv#glmnet 113.42926 -3.154990
## All.X##rcv#glm 771.99279 -191.218920
## max.Rsquared.fit min.RMSESD.fit
## Max.cor.Y.rcv.1X1###glmnet NA NA
## Max.cor.Y##rcv#rpart 0.8083695 1.593100
## Max.cor.Y.Time.Lag##rcv#glmnet 0.4436578 1.961742
## Interact.High.cor.Y##rcv#glmnet 0.6129020 1.459778
## Low.cor.X##rcv#glmnet 0.4367487 2.060214
## All.X##rcv#glmnet 0.4367487 2.060214
## All.X##rcv#glm 0.4337656 2.014089
## max.RsquaredSD.fit min.aic.fit
## Max.cor.Y.rcv.1X1###glmnet NA NA
## Max.cor.Y##rcv#rpart 0.03917691 NA
## Max.cor.Y.Time.Lag##rcv#glmnet 0.02100110 NA
## Interact.High.cor.Y##rcv#glmnet 0.03746229 NA
## Low.cor.X##rcv#glmnet 0.01913324 NA
## All.X##rcv#glmnet 0.01913324 NA
## All.X##rcv#glm 0.01975136 24768.3rm(ret_lst)
fit.models_1_chunk_df <-
myadd_chunk(fit.models_1_chunk_df, "fit.models_1_end", major.inc = FALSE,
label.minor = "teardown")## label step_major step_minor label_minor bgn end
## 5 fit.models_1_preProc 1 4 preProc 143.384 143.446
## 6 fit.models_1_end 1 5 teardown 143.447 NA
## elapsed
## 5 0.062
## 6 NAglb_chunks_df <- myadd_chunk(glb_chunks_df, "fit.models", major.inc = FALSE)## label step_major step_minor label_minor bgn end elapsed
## 17 fit.models 8 1 1 134.981 143.455 8.474
## 18 fit.models 8 2 2 143.456 NA NAfit.models_2_chunk_df <-
myadd_chunk(NULL, "fit.models_2_bgn", label.minor = "setup")## label step_major step_minor label_minor bgn end elapsed
## 1 fit.models_2_bgn 1 0 setup 145.093 NA NAplt_models_df <- glb_models_df[, -grep("SD|Upper|Lower", names(glb_models_df))]
for (var in grep("^min.", names(plt_models_df), value=TRUE)) {
plt_models_df[, sub("min.", "inv.", var)] <-
#ifelse(all(is.na(tmp <- plt_models_df[, var])), NA, 1.0 / tmp)
1.0 / plt_models_df[, var]
plt_models_df <- plt_models_df[ , -grep(var, names(plt_models_df))]
}
print(plt_models_df)## id
## Max.cor.Y.rcv.1X1###glmnet Max.cor.Y.rcv.1X1###glmnet
## Max.cor.Y##rcv#rpart Max.cor.Y##rcv#rpart
## Max.cor.Y.Time.Lag##rcv#glmnet Max.cor.Y.Time.Lag##rcv#glmnet
## Interact.High.cor.Y##rcv#glmnet Interact.High.cor.Y##rcv#glmnet
## Low.cor.X##rcv#glmnet Low.cor.X##rcv#glmnet
## All.X##rcv#glmnet All.X##rcv#glmnet
## All.X##rcv#glm All.X##rcv#glm
## feats
## Max.cor.Y.rcv.1X1###glmnet .pos,.inp.fctr
## Max.cor.Y##rcv#rpart .pos,.inp.fctr
## Max.cor.Y.Time.Lag##rcv#glmnet .pos,.inp.fctr,Date.last2.log1p,Date.last4.log1p,Date.last8.log1p,Date.last16.log1p,Date.last32.log1p
## Interact.High.cor.Y##rcv#glmnet .pos,.inp.fctr,.pos:.pos,.pos:Date.last2.log1p,.pos:.inp.fctr,.pos:Date.month.fctr
## Low.cor.X##rcv#glmnet .inp.fctr,Date.last2.log1p,Date.last32.log1p,Date.last4.log1p,Date.wkday.fctr,Date.wkend,.rnorm,Date.last8.log1p,Date.last16.log1p,Date.juliandate,Date.month.fctr,.pos,.pos.y,.rownames
## All.X##rcv#glmnet .inp.fctr,Date.last2.log1p,Date.last32.log1p,Date.last4.log1p,Date.wkday.fctr,Date.wkend,.rnorm,Date.last8.log1p,Date.last16.log1p,Date.juliandate,Date.month.fctr,.pos,.pos.y,.rownames
## All.X##rcv#glm .inp.fctr,Date.last2.log1p,Date.last32.log1p,Date.last4.log1p,Date.wkday.fctr,Date.wkend,.rnorm,Date.last8.log1p,Date.last16.log1p,Date.juliandate,Date.month.fctr,.pos,.pos.y,.rownames
## max.nTuningRuns max.R.sq.fit
## Max.cor.Y.rcv.1X1###glmnet 0 0.4354461
## Max.cor.Y##rcv#rpart 5 0.8113283
## Max.cor.Y.Time.Lag##rcv#glmnet 25 0.4456674
## Interact.High.cor.Y##rcv#glmnet 25 0.6172344
## Low.cor.X##rcv#glmnet 25 0.4460000
## All.X##rcv#glmnet 25 0.4460000
## All.X##rcv#glm 1 0.4484718
## max.Adj.R.sq.fit max.R.sq.OOB
## Max.cor.Y.rcv.1X1###glmnet 0.4342670 -5.8717963
## Max.cor.Y##rcv#rpart NA -0.2678863
## Max.cor.Y.Time.Lag##rcv#glmnet 0.4433471 -16.2004933
## Interact.High.cor.Y##rcv#glmnet 0.6138542 -45.4530763
## Low.cor.X##rcv#glmnet 0.4385103 -3.0995666
## All.X##rcv#glmnet 0.4385103 -3.0995666
## All.X##rcv#glm 0.4417231 -188.8953069
## max.Adj.R.sq.OOB max.Rsquared.fit
## Max.cor.Y.rcv.1X1###glmnet -5.886148 NA
## Max.cor.Y##rcv#rpart NA 0.8083695
## Max.cor.Y.Time.Lag##rcv#glmnet -16.272492 0.4436578
## Interact.High.cor.Y##rcv#glmnet -45.863301 0.6129020
## Low.cor.X##rcv#glmnet -3.154990 0.4367487
## All.X##rcv#glmnet -3.154990 0.4367487
## All.X##rcv#glm -191.218920 0.4337656
## inv.elapsedtime.everything
## Max.cor.Y.rcv.1X1###glmnet 1.5243902
## Max.cor.Y##rcv#rpart 0.6075334
## Max.cor.Y.Time.Lag##rcv#glmnet 0.4231909
## Interact.High.cor.Y##rcv#glmnet 0.4899559
## Low.cor.X##rcv#glmnet 0.4253509
## All.X##rcv#glmnet 0.4889976
## All.X##rcv#glm 0.7168459
## inv.elapsedtime.final inv.RMSE.fit
## Max.cor.Y.rcv.1X1###glmnet 90.90909 0.02375698
## Max.cor.Y##rcv#rpart 50.00000 0.04115242
## Max.cor.Y.Time.Lag##rcv#glmnet 125.00000 0.02391502
## Interact.High.cor.Y##rcv#glmnet 66.66667 0.02866791
## Low.cor.X##rcv#glmnet 83.33333 0.02376566
## All.X##rcv#glmnet 83.33333 0.02376566
## All.X##rcv#glm 29.41176 0.02369499
## inv.RMSE.OOB inv.aic.fit
## Max.cor.Y.rcv.1X1###glmnet 0.006809398 NA
## Max.cor.Y##rcv#rpart 0.015852717 NA
## Max.cor.Y.Time.Lag##rcv#glmnet 0.004304011 NA
## Interact.High.cor.Y##rcv#glmnet 0.002619007 NA
## Low.cor.X##rcv#glmnet 0.008816067 NA
## All.X##rcv#glmnet 0.008816067 NA
## All.X##rcv#glm 0.001295349 4.037419e-05# print(myplot_radar(radar_inp_df=plt_models_df))
# print(myplot_radar(radar_inp_df=subset(plt_models_df,
# !(mdl_id %in% grep("random|MFO", plt_models_df$id, value=TRUE)))))
# Compute CI for <metric>SD
glb_models_df <- mutate(glb_models_df,
max.df = ifelse(max.nTuningRuns > 1, max.nTuningRuns - 1, NA),
min.sd2ci.scaler = ifelse(is.na(max.df), NA, qt(0.975, max.df)))
for (var in grep("SD", names(glb_models_df), value=TRUE)) {
# Does CI alredy exist ?
var_components <- unlist(strsplit(var, "SD"))
varActul <- paste0(var_components[1], var_components[2])
varUpper <- paste0(var_components[1], "Upper", var_components[2])
varLower <- paste0(var_components[1], "Lower", var_components[2])
if (varUpper %in% names(glb_models_df)) {
warning(varUpper, " already exists in glb_models_df")
# Assuming Lower also exists
next
}
print(sprintf("var:%s", var))
# CI is dependent on sample size in t distribution; df=n-1
glb_models_df[, varUpper] <- glb_models_df[, varActul] +
glb_models_df[, "min.sd2ci.scaler"] * glb_models_df[, var]
glb_models_df[, varLower] <- glb_models_df[, varActul] -
glb_models_df[, "min.sd2ci.scaler"] * glb_models_df[, var]
}## [1] "var:min.RMSESD.fit"
## [1] "var:max.RsquaredSD.fit"# Plot metrics with CI
plt_models_df <- glb_models_df[, "id", FALSE]
pltCI_models_df <- glb_models_df[, "id", FALSE]
for (var in grep("Upper", names(glb_models_df), value=TRUE)) {
var_components <- unlist(strsplit(var, "Upper"))
col_name <- unlist(paste(var_components, collapse=""))
plt_models_df[, col_name] <- glb_models_df[, col_name]
for (name in paste0(var_components[1], c("Upper", "Lower"), var_components[2]))
pltCI_models_df[, name] <- glb_models_df[, name]
}
build_statsCI_data <- function(plt_models_df) {
mltd_models_df <- melt(plt_models_df, id.vars="id")
mltd_models_df$data <- sapply(1:nrow(mltd_models_df),
function(row_ix) tail(unlist(strsplit(as.character(
mltd_models_df[row_ix, "variable"]), "[.]")), 1))
mltd_models_df$label <- sapply(1:nrow(mltd_models_df),
function(row_ix) head(unlist(strsplit(as.character(
mltd_models_df[row_ix, "variable"]),
paste0(".", mltd_models_df[row_ix, "data"]))), 1))
#print(mltd_models_df)
return(mltd_models_df)
}
mltd_models_df <- build_statsCI_data(plt_models_df)
mltdCI_models_df <- melt(pltCI_models_df, id.vars="id")
for (row_ix in 1:nrow(mltdCI_models_df)) {
for (type in c("Upper", "Lower")) {
if (length(var_components <- unlist(strsplit(
as.character(mltdCI_models_df[row_ix, "variable"]), type))) > 1) {
#print(sprintf("row_ix:%d; type:%s; ", row_ix, type))
mltdCI_models_df[row_ix, "label"] <- var_components[1]
mltdCI_models_df[row_ix, "data"] <-
unlist(strsplit(var_components[2], "[.]"))[2]
mltdCI_models_df[row_ix, "type"] <- type
break
}
}
}
wideCI_models_df <- reshape(subset(mltdCI_models_df, select=-variable),
timevar="type",
idvar=setdiff(names(mltdCI_models_df), c("type", "value", "variable")),
direction="wide")
#print(wideCI_models_df)
mrgdCI_models_df <- merge(wideCI_models_df, mltd_models_df, all.x=TRUE)
#print(mrgdCI_models_df)
# Merge stats back in if CIs don't exist
goback_vars <- c()
for (var in unique(mltd_models_df$label)) {
for (type in unique(mltd_models_df$data)) {
var_type <- paste0(var, ".", type)
# if this data is already present, next
if (var_type %in% unique(paste(mltd_models_df$label, mltd_models_df$data,
sep=".")))
next
#print(sprintf("var_type:%s", var_type))
goback_vars <- c(goback_vars, var_type)
}
}
if (length(goback_vars) > 0) {
mltd_goback_df <- build_statsCI_data(glb_models_df[, c("id", goback_vars)])
mltd_models_df <- rbind(mltd_models_df, mltd_goback_df)
}
# mltd_models_df <- merge(mltd_models_df, glb_models_df[, c("id", "model_method")],
# all.x=TRUE)
png(paste0(glbOut$pfx, "models_bar.png"), width=480*3, height=480*2)
#print(gp <- myplot_bar(mltd_models_df, "id", "value", colorcol_name="model_method") +
print(gp <- myplot_bar(df=mltd_models_df, xcol_name="id", ycol_names="value") +
geom_errorbar(data=mrgdCI_models_df,
mapping=aes(x=mdl_id, ymax=value.Upper, ymin=value.Lower), width=0.5) +
facet_grid(label ~ data, scales="free") +
theme(axis.text.x = element_text(angle = 90,vjust = 0.5)))## Warning: Removed 1 rows containing missing values (position_stack).## Warning: Removed 4 rows containing missing values (geom_errorbar).dev.off()## quartz_off_screen
## 2print(gp)## Warning: Removed 1 rows containing missing values (position_stack).
## Warning: Removed 4 rows containing missing values (geom_errorbar).
dsp_models_cols <- c("id",
glbMdlMetricsEval[glbMdlMetricsEval %in% names(glb_models_df)],
grep("opt.", names(glb_models_df), fixed = TRUE, value = TRUE))
# if (glb_is_classification && glb_is_binomial)
# dsp_models_cols <- c(dsp_models_cols, "opt.prob.threshold.OOB")
print(dsp_models_df <- orderBy(get_model_sel_frmla(), glb_models_df)[, dsp_models_cols])## id min.RMSE.OOB max.R.sq.OOB
## 2 Max.cor.Y##rcv#rpart 63.08067 -0.2678863
## 5 Low.cor.X##rcv#glmnet 113.42926 -3.0995666
## 6 All.X##rcv#glmnet 113.42926 -3.0995666
## 1 Max.cor.Y.rcv.1X1###glmnet 146.85585 -5.8717963
## 3 Max.cor.Y.Time.Lag##rcv#glmnet 232.34139 -16.2004933
## 4 Interact.High.cor.Y##rcv#glmnet 381.82413 -45.4530763
## 7 All.X##rcv#glm 771.99279 -188.8953069
## max.Adj.R.sq.fit min.RMSE.fit
## 2 NA 24.29990
## 5 0.4385103 42.07752
## 6 0.4385103 42.07752
## 1 0.4342670 42.09290
## 3 0.4433471 41.81473
## 4 0.6138542 34.88221
## 7 0.4417231 42.20301# print(myplot_radar(radar_inp_df = dsp_models_df))
print("Metrics used for model selection:"); print(get_model_sel_frmla())## [1] "Metrics used for model selection:"## ~+min.RMSE.OOB - max.R.sq.OOB - max.Adj.R.sq.fit + min.RMSE.fit
## <environment: 0x7fa5ecee0260>print(sprintf("Best model id: %s", dsp_models_df[1, "id"]))## [1] "Best model id: Max.cor.Y##rcv#rpart"glb_get_predictions <- function(df, mdl_id, rsp_var, prob_threshold_def=NULL, verbose=FALSE) {
mdl <- glb_models_lst[[mdl_id]]
clmnNames <- mygetPredictIds(rsp_var, mdl_id)
predct_var_name <- clmnNames$value
predct_prob_var_name <- clmnNames$prob
predct_accurate_var_name <- clmnNames$is.acc
predct_error_var_name <- clmnNames$err
predct_erabs_var_name <- clmnNames$err.abs
if (glb_is_regression) {
df[, predct_var_name] <- predict(mdl, newdata=df, type="raw")
if (verbose) print(myplot_scatter(df, glb_rsp_var, predct_var_name) +
facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
stat_smooth(method="glm"))
df[, predct_error_var_name] <- df[, predct_var_name] - df[, glb_rsp_var]
if (verbose) print(myplot_scatter(df, predct_var_name, predct_error_var_name) +
#facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
stat_smooth(method="auto"))
if (verbose) print(myplot_scatter(df, glb_rsp_var, predct_error_var_name) +
#facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
stat_smooth(method="glm"))
df[, predct_erabs_var_name] <- abs(df[, predct_error_var_name])
if (verbose) print(head(orderBy(reformulate(c("-", predct_erabs_var_name)), df)))
df[, predct_accurate_var_name] <- (df[, glb_rsp_var] == df[, predct_var_name])
}
if (glb_is_classification && glb_is_binomial) {
prob_threshold <- glb_models_df[glb_models_df$id == mdl_id,
"opt.prob.threshold.OOB"]
if (is.null(prob_threshold) || is.na(prob_threshold)) {
warning("Using default probability threshold: ", prob_threshold_def)
if (is.null(prob_threshold <- prob_threshold_def))
stop("Default probability threshold is NULL")
}
df[, predct_prob_var_name] <- predict(mdl, newdata = df, type = "prob")[, 2]
df[, predct_var_name] <-
factor(levels(df[, glb_rsp_var])[
(df[, predct_prob_var_name] >=
prob_threshold) * 1 + 1], levels(df[, glb_rsp_var]))
# if (verbose) print(myplot_scatter(df, glb_rsp_var, predct_var_name) +
# facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
# stat_smooth(method="glm"))
df[, predct_error_var_name] <- df[, predct_var_name] != df[, glb_rsp_var]
# if (verbose) print(myplot_scatter(df, predct_var_name, predct_error_var_name) +
# #facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
# stat_smooth(method="auto"))
# if (verbose) print(myplot_scatter(df, glb_rsp_var, predct_error_var_name) +
# #facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
# stat_smooth(method="glm"))
# if prediction is a TP (true +ve), measure distance from 1.0
tp <- which((df[, predct_var_name] == df[, glb_rsp_var]) &
(df[, predct_var_name] == levels(df[, glb_rsp_var])[2]))
df[tp, predct_erabs_var_name] <- abs(1 - df[tp, predct_prob_var_name])
#rowIx <- which.max(df[tp, predct_erabs_var_name]); df[tp, c(glbFeatsId, glb_rsp_var, predct_var_name, predct_prob_var_name, predct_erabs_var_name)][rowIx, ]
# if prediction is a TN (true -ve), measure distance from 0.0
tn <- which((df[, predct_var_name] == df[, glb_rsp_var]) &
(df[, predct_var_name] == levels(df[, glb_rsp_var])[1]))
df[tn, predct_erabs_var_name] <- abs(0 - df[tn, predct_prob_var_name])
#rowIx <- which.max(df[tn, predct_erabs_var_name]); df[tn, c(glbFeatsId, glb_rsp_var, predct_var_name, predct_prob_var_name, predct_erabs_var_name)][rowIx, ]
# if prediction is a FP (flse +ve), measure distance from 0.0
fp <- which((df[, predct_var_name] != df[, glb_rsp_var]) &
(df[, predct_var_name] == levels(df[, glb_rsp_var])[2]))
df[fp, predct_erabs_var_name] <- abs(0 - df[fp, predct_prob_var_name])
#rowIx <- which.max(df[fp, predct_erabs_var_name]); df[fp, c(glbFeatsId, glb_rsp_var, predct_var_name, predct_prob_var_name, predct_erabs_var_name)][rowIx, ]
# if prediction is a FN (flse -ve), measure distance from 1.0
fn <- which((df[, predct_var_name] != df[, glb_rsp_var]) &
(df[, predct_var_name] == levels(df[, glb_rsp_var])[1]))
df[fn, predct_erabs_var_name] <- abs(1 - df[fn, predct_prob_var_name])
#rowIx <- which.max(df[fn, predct_erabs_var_name]); df[fn, c(glbFeatsId, glb_rsp_var, predct_var_name, predct_prob_var_name, predct_erabs_var_name)][rowIx, ]
if (verbose) print(head(orderBy(reformulate(c("-", predct_erabs_var_name)), df)))
df[, predct_accurate_var_name] <- (df[, glb_rsp_var] == df[, predct_var_name])
}
if (glb_is_classification && !glb_is_binomial) {
df[, predct_var_name] <- predict(mdl, newdata = df, type = "raw")
probCls <- predict(mdl, newdata = df, type = "prob")
df[, predct_prob_var_name] <- NA
for (cls in names(probCls)) {
mask <- (df[, predct_var_name] == cls)
df[mask, predct_prob_var_name] <- probCls[mask, cls]
}
if (verbose) print(myplot_histogram(df, predct_prob_var_name,
fill_col_name = predct_var_name))
if (verbose) print(myplot_histogram(df, predct_prob_var_name,
facet_frmla = paste0("~", glb_rsp_var)))
df[, predct_error_var_name] <- df[, predct_var_name] != df[, glb_rsp_var]
# if prediction is erroneous, measure predicted class prob from actual class prob
df[, predct_erabs_var_name] <- 0
for (cls in names(probCls)) {
mask <- (df[, glb_rsp_var] == cls) & (df[, predct_error_var_name])
df[mask, predct_erabs_var_name] <- probCls[mask, cls]
}
df[, predct_accurate_var_name] <- (df[, glb_rsp_var] == df[, predct_var_name])
}
return(df)
}
#stop(here"); glb2Sav(); glbObsAll <- savObsAll; glbObsTrn <- savObsTrn; glbObsFit <- savObsFit; glbObsOOB <- savObsOOB; sav_models_df <- glb_models_df; glb_models_df <- sav_models_df; glb_featsimp_df <- sav_featsimp_df
myget_category_stats <- function(obs_df, mdl_id, label) {
require(dplyr)
require(lazyeval)
predct_var_name <- mygetPredictIds(glb_rsp_var, mdl_id)$value
predct_error_var_name <- mygetPredictIds(glb_rsp_var, mdl_id)$err.abs
if (!predct_var_name %in% names(obs_df))
obs_df <- glb_get_predictions(obs_df, mdl_id, glb_rsp_var)
tmp_obs_df <- obs_df[, c(glbFeatsCategory, glb_rsp_var,
predct_var_name, predct_error_var_name)]
# tmp_obs_df <- obs_df %>%
# dplyr::select_(glbFeatsCategory, glb_rsp_var, predct_var_name, predct_error_var_name)
#dplyr::rename(startprice.log10.predict.RFE.X.glmnet.err=error_abs_OOB)
names(tmp_obs_df)[length(names(tmp_obs_df))] <- paste0("err.abs.", label)
ret_ctgry_df <- tmp_obs_df %>%
dplyr::group_by_(glbFeatsCategory) %>%
dplyr::summarise_(#interp(~sum(abs(var)), var=as.name(glb_rsp_var)),
interp(~sum(var), var=as.name(paste0("err.abs.", label))),
interp(~mean(var), var=as.name(paste0("err.abs.", label))),
interp(~n()))
names(ret_ctgry_df) <- c(glbFeatsCategory,
#paste0(glb_rsp_var, ".abs.", label, ".sum"),
paste0("err.abs.", label, ".sum"),
paste0("err.abs.", label, ".mean"),
paste0(".n.", label))
ret_ctgry_df <- dplyr::ungroup(ret_ctgry_df)
#colSums(ret_ctgry_df[, -grep(glbFeatsCategory, names(ret_ctgry_df))])
return(ret_ctgry_df)
}
#print(colSums((ctgry_df <- myget_category_stats(obs_df=glbObsFit, mdl_id="", label="fit"))[, -grep(glbFeatsCategory, names(ctgry_df))]))
if (!is.null(glb_mdl_ensemble)) {
fit.models_2_chunk_df <- myadd_chunk(fit.models_2_chunk_df,
paste0("fit.models_2_", mdl_id_pfx), major.inc = TRUE,
label.minor = "ensemble")
mdl_id_pfx <- "Ensemble"
if (#(glb_is_regression) |
((glb_is_classification) & (!glb_is_binomial)))
stop("Ensemble models not implemented yet for multinomial classification")
mygetEnsembleAutoMdlIds <- function() {
tmp_models_df <- orderBy(get_model_sel_frmla(), glb_models_df)
row.names(tmp_models_df) <- tmp_models_df$id
mdl_threshold_pos <-
min(which(grepl("MFO|Random|Baseline", tmp_models_df$id))) - 1
mdlIds <- tmp_models_df$id[1:mdl_threshold_pos]
return(mdlIds[!grepl("Ensemble", mdlIds)])
}
if (glb_mdl_ensemble == "auto") {
glb_mdl_ensemble <- mygetEnsembleAutoMdlIds()
mdl_id_pfx <- paste0(mdl_id_pfx, ".auto")
} else if (grepl("^%<d-%", glb_mdl_ensemble)) {
glb_mdl_ensemble <- eval(parse(text =
str_trim(unlist(strsplit(glb_mdl_ensemble, "%<d-%"))[2])))
}
for (mdl_id in glb_mdl_ensemble) {
if (!(mdl_id %in% names(glb_models_lst))) {
warning("Model ", mdl_id, " in glb_model_ensemble not found !")
next
}
glbObsFit <- glb_get_predictions(df = glbObsFit, mdl_id, glb_rsp_var)
glbObsOOB <- glb_get_predictions(df = glbObsOOB, mdl_id, glb_rsp_var)
}
#mdl_id_pfx <- "Ensemble.RFE"; mdlId <- paste0(mdl_id_pfx, ".glmnet")
#glb_mdl_ensemble <- gsub(mygetPredictIds$value, "", grep("RFE\\.X\\.(?!Interact)", row.names(glb_featsimp_df), perl = TRUE, value = TRUE), fixed = TRUE)
#varImp(glb_models_lst[[mdlId]])
#cor_df <- data.frame(cor=cor(glbObsFit[, glb_rsp_var], glbObsFit[, paste(mygetPredictIds$value, glb_mdl_ensemble)], use="pairwise.complete.obs"))
#glbObsFit <- glb_get_predictions(df=glbObsFit, "Ensemble.glmnet", glb_rsp_var);print(colSums((ctgry_df <- myget_category_stats(obs_df=glbObsFit, mdl_id="Ensemble.glmnet", label="fit"))[, -grep(glbFeatsCategory, names(ctgry_df))]))
### bid0_sp
# Better than MFO; models.n=28; min.RMSE.fit=0.0521233; err.abs.fit.sum=7.3631895
# old: Top x from auto; models.n= 5; min.RMSE.fit=0.06311047; err.abs.fit.sum=9.5937080
# RFE only ; models.n=16; min.RMSE.fit=0.05148588; err.abs.fit.sum=7.2875091
# RFE subset only ;models.n= 5; min.RMSE.fit=0.06040702; err.abs.fit.sum=9.059088
# RFE subset only ;models.n= 9; min.RMSE.fit=0.05933167; err.abs.fit.sum=8.7421288
# RFE subset only ;models.n=15; min.RMSE.fit=0.0584607; err.abs.fit.sum=8.5902066
# RFE subset only ;models.n=17; min.RMSE.fit=0.05496899; err.abs.fit.sum=8.0170431
# RFE subset only ;models.n=18; min.RMSE.fit=0.05441577; err.abs.fit.sum=7.837223
# RFE subset only ;models.n=16; min.RMSE.fit=0.05441577; err.abs.fit.sum=7.837223
### bid0_sp
### bid1_sp
# "auto"; err.abs.fit.sum=76.699774; min.RMSE.fit=0.2186429
# "RFE.X.*"; err.abs.fit.sum=; min.RMSE.fit=0.221114
### bid1_sp
indepVar <- paste(mygetPredictIds(glb_rsp_var)$value, glb_mdl_ensemble, sep = "")
if (glb_is_classification)
indepVar <- paste(indepVar, ".prob", sep = "")
# Some models in glb_mdl_ensemble might not be fitted e.g. RFE.X.Interact
indepVar <- intersect(indepVar, names(glbObsFit))
# indepVar <- grep(mygetPredictIds(glb_rsp_var)$value, names(glbObsFit), fixed=TRUE, value=TRUE)
# if (glb_is_regression)
# indepVar <- indepVar[!grepl("(err\\.abs|accurate)$", indepVar)]
# if (glb_is_classification && glb_is_binomial)
# indepVar <- grep("prob$", indepVar, value=TRUE) else
# indepVar <- indepVar[!grepl("err$", indepVar)]
#rfe_fit_ens_results <- myrun_rfe(glbObsFit, indepVar)
for (method in c("glm", "glmnet")) {
for (trainControlMethod in
c("boot", "boot632", "cv", "repeatedcv"
#, "LOOCV" # tuneLength * nrow(fitDF)
, "LGOCV", "adaptive_cv"
#, "adaptive_boot" #error: adaptive$min should be less than 3
#, "adaptive_LGOCV" #error: adaptive$min should be less than 3
)) {
#sav_models_df <- glb_models_df; all.equal(sav_models_df, glb_models_df)
#glb_models_df <- sav_models_df; print(glb_models_df$id)
if ((method == "glm") && (trainControlMethod != "repeatedcv"))
# glm used only to identify outliers
next
ret_lst <- myfit_mdl(
mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = paste0(mdl_id_pfx, ".", trainControlMethod),
type = glb_model_type, tune.df = NULL,
trainControl.method = trainControlMethod,
trainControl.number = glb_rcv_n_folds,
trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = method)),
indepVar = indepVar, rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}
}
dsp_models_df <- get_dsp_models_df()
}
if (is.null(glb_sel_mdl_id))
glb_sel_mdl_id <- dsp_models_df[1, "id"] else
print(sprintf("User specified selection: %s", glb_sel_mdl_id)) ## [1] "User specified selection: All.X##rcv#glmnet"myprint_mdl(glb_sel_mdl <- glb_models_lst[[glb_sel_mdl_id]])
## Length Class Mode
## a0 86 -none- numeric
## beta 2752 dgCMatrix S4
## df 86 -none- numeric
## dim 2 -none- numeric
## lambda 86 -none- numeric
## dev.ratio 86 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 32 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 1 -none- logical
## [1] "min lambda > lambdaOpt:"
## (Intercept) .inp.fctrCC .inp.fctrGE .pos
## 1.798626e+03 2.238909e+01 -4.421574e+01 -7.255471e-02
## .rnorm .rownames Date.juliandate Date.last16.log1p
## 5.052143e-01 -1.215360e-02 -6.392147e-03 -1.013606e+02
## Date.last2.log1p Date.last4.log1p Date.month.fctr02 Date.month.fctr03
## -1.002126e+00 -3.358519e+00 3.029397e+00 -6.075795e-01
## Date.month.fctr05 Date.month.fctr06 Date.month.fctr07 Date.month.fctr08
## 1.717577e+00 -6.067895e-01 -1.042922e+00 -4.149733e-01
## Date.month.fctr10 Date.month.fctr12 Date.wkday.fctr4 Date.wkday.fctr6
## -1.120237e+00 6.543330e-01 1.070070e+00 3.014252e-01
## [1] "max lambda < lambdaOpt:"
## (Intercept) .inp.fctrCC .inp.fctrGE .pos
## 1.841415e+03 2.294225e+01 -4.373128e+01 -7.327536e-02
## .rnorm .rownames Date.juliandate Date.last16.log1p
## 5.163244e-01 -1.248840e-02 -6.428555e-03 -1.039757e+02
## Date.last2.log1p Date.last4.log1p Date.month.fctr02 Date.month.fctr03
## -1.069648e+00 -3.430272e+00 3.092951e+00 -7.588476e-01
## Date.month.fctr05 Date.month.fctr06 Date.month.fctr07 Date.month.fctr08
## 1.741870e+00 -6.652235e-01 -1.102323e+00 -4.689666e-01
## Date.month.fctr10 Date.month.fctr12 Date.wkday.fctr4 Date.wkday.fctr6
## -1.172213e+00 6.976209e-01 1.113995e+00 3.503962e-01## [1] TRUE# From here to save(), this should all be in one function
# these are executed in the same seq twice more:
# fit.data.training & predict.data.new chunks
print(sprintf("%s fit prediction diagnostics:", glb_sel_mdl_id))## [1] "All.X##rcv#glmnet fit prediction diagnostics:"glbObsFit <- glb_get_predictions(df = glbObsFit, mdl_id = glb_sel_mdl_id,
rsp_var = glb_rsp_var)
print(sprintf("%s OOB prediction diagnostics:", glb_sel_mdl_id))## [1] "All.X##rcv#glmnet OOB prediction diagnostics:"glbObsOOB <- glb_get_predictions(df = glbObsOOB, mdl_id = glb_sel_mdl_id,
rsp_var = glb_rsp_var)
print(glb_featsimp_df <- myget_feats_importance(mdl = glb_sel_mdl, featsimp_df = NULL))## All.X..rcv.glmnet.imp imp
## Date.last16.log1p 1.000000e+02 1.000000e+02
## .inp.fctrGE 4.273554e+01 4.273554e+01
## .inp.fctrCC 2.207520e+01 2.207520e+01
## Date.last4.log1p 3.305309e+00 3.305309e+00
## Date.month.fctr02 2.980765e+00 2.980765e+00
## Date.month.fctr05 1.683599e+00 1.683599e+00
## Date.month.fctr10 1.117788e+00 1.117788e+00
## Date.wkday.fctr4 1.064609e+00 1.064609e+00
## Date.month.fctr07 1.046650e+00 1.046650e+00
## Date.last2.log1p 1.011407e+00 1.011407e+00
## Date.month.fctr03 6.733998e-01 6.733998e-01
## Date.month.fctr12 6.599563e-01 6.599563e-01
## Date.month.fctr06 6.219835e-01 6.219835e-01
## .rnorm 4.973828e-01 4.973828e-01
## Date.month.fctr08 4.330194e-01 4.330194e-01
## Date.wkday.fctr6 3.198537e-01 3.198537e-01
## .pos 7.095269e-02 7.095269e-02
## .rownames 1.200204e-02 1.200204e-02
## Date.juliandate 6.236232e-03 6.236232e-03
## .inp.fctrIBM 0.000000e+00 0.000000e+00
## .inp.fctrPG 0.000000e+00 0.000000e+00
## .pos.y 0.000000e+00 0.000000e+00
## Date.last32.log1p 0.000000e+00 0.000000e+00
## Date.last8.log1p 0.000000e+00 0.000000e+00
## Date.month.fctr04 0.000000e+00 0.000000e+00
## Date.month.fctr09 0.000000e+00 0.000000e+00
## Date.month.fctr11 0.000000e+00 0.000000e+00
## Date.wkday.fctr1 0.000000e+00 0.000000e+00
## Date.wkday.fctr2 0.000000e+00 0.000000e+00
## Date.wkday.fctr3 0.000000e+00 0.000000e+00
## Date.wkday.fctr5 0.000000e+00 0.000000e+00
## Date.wkend 0.000000e+00 0.000000e+00#mdl_id <-"RFE.X.glmnet"; glb_featsimp_df <- myget_feats_importance(glb_models_lst[[mdl_id]], glb_featsimp_df); glb_featsimp_df[, paste0(mdl_id, ".imp")] <- glb_featsimp_df$imp; print(glb_featsimp_df)
#print(head(sbst_featsimp_df <- subset(glb_featsimp_df, is.na(RFE.X.glmnet.imp) | (abs(RFE.X.YeoJohnson.glmnet.imp - RFE.X.glmnet.imp) > 0.0001), select=-imp)))
#print(orderBy(~ -cor.y.abs, subset(glb_feats_df, id %in% c(row.names(sbst_featsimp_df), "startprice.dcm1.is9", "D.weight.post.stop.sum"))))
# Used again in fit.data.training & predict.data.new chunks
glb_analytics_diag_plots <- function(obs_df, mdl_id, prob_threshold=NULL) {
if (!is.null(featsimp_df <- glb_featsimp_df)) {
featsimp_df$feat <- gsub("`(.*?)`", "\\1", row.names(featsimp_df))
featsimp_df$feat.interact <- gsub("(.*?):(.*)", "\\2", featsimp_df$feat)
featsimp_df$feat <- gsub("(.*?):(.*)", "\\1", featsimp_df$feat)
featsimp_df$feat.interact <-
ifelse(featsimp_df$feat.interact == featsimp_df$feat,
NA, featsimp_df$feat.interact)
featsimp_df$feat <-
gsub("(.*?)\\.fctr(.*)", "\\1\\.fctr", featsimp_df$feat)
featsimp_df$feat.interact <-
gsub("(.*?)\\.fctr(.*)", "\\1\\.fctr", featsimp_df$feat.interact)
featsimp_df <- orderBy(~ -imp.max,
summaryBy(imp ~ feat + feat.interact, data=featsimp_df,
FUN=max))
#rex_str=":(.*)"; txt_vctr=tail(featsimp_df$feat); ret_lst <- regexec(rex_str, txt_vctr); ret_lst <- regmatches(txt_vctr, ret_lst); ret_vctr <- sapply(1:length(ret_lst), function(pos_ix) ifelse(length(ret_lst[[pos_ix]]) > 0, ret_lst[[pos_ix]], "")); print(ret_vctr <- ret_vctr[ret_vctr != ""])
featsimp_df <- subset(featsimp_df, !is.na(imp.max))
if (nrow(featsimp_df) > 5) {
warning("Limiting important feature scatter plots to 5 out of ",
nrow(featsimp_df))
featsimp_df <- head(featsimp_df, 5)
}
# if (!all(is.na(featsimp_df$feat.interact)))
# stop("not implemented yet")
rsp_var_out <- mygetPredictIds(glb_rsp_var, mdl_id)$value
for (var in featsimp_df$feat) {
plot_df <- melt(obs_df, id.vars = var,
measure.vars = c(glb_rsp_var, rsp_var_out))
print(myplot_scatter(plot_df, var, "value", colorcol_name = "variable",
facet_colcol_name = "variable", jitter = TRUE) +
guides(color = FALSE))
}
}
if (glb_is_regression) {
if (is.null(featsimp_df) || (nrow(featsimp_df) == 0))
warning("No important features in glb_fin_mdl") else
print(myplot_prediction_regression(df=obs_df,
feat_x=ifelse(nrow(featsimp_df) > 1, featsimp_df$feat[2],
".rownames"),
feat_y=featsimp_df$feat[1],
rsp_var=glb_rsp_var, rsp_var_out=rsp_var_out,
id_vars=glbFeatsId)
# + facet_wrap(reformulate(featsimp_df$feat[2])) # if [1 or 2] is a factor
# + geom_point(aes_string(color="<col_name>.fctr")) # to color the plot
)
}
if (glb_is_classification) {
if (is.null(featsimp_df) || (nrow(featsimp_df) == 0))
warning("No features in selected model are statistically important")
else print(myplot_prediction_classification(df = obs_df,
feat_x = ifelse(nrow(featsimp_df) > 1,
featsimp_df$feat[2], ".rownames"),
feat_y = featsimp_df$feat[1],
rsp_var = glb_rsp_var,
rsp_var_out = rsp_var_out,
id_vars = glbFeatsId,
prob_threshold = prob_threshold))
}
}
if (glb_is_classification && glb_is_binomial)
glb_analytics_diag_plots(obs_df = glbObsOOB, mdl_id = glb_sel_mdl_id,
prob_threshold = glb_models_df[glb_models_df$id == glb_sel_mdl_id,
"opt.prob.threshold.OOB"]) else
glb_analytics_diag_plots(obs_df = glbObsOOB, mdl_id = glb_sel_mdl_id) ## Warning in glb_analytics_diag_plots(obs_df = glbObsOOB, mdl_id =
## glb_sel_mdl_id): Limiting important feature scatter plots to 5 out of 14
## Date StockPrice .inp .src .rnorm .pos .pos.y .rownames
## 2438 2/1/73 438.9016 IBM Test -0.4353803 2438 2438 2438
## 2439 3/1/73 437.4041 IBM Test 0.2302633 2439 2439 2439
## 2437 1/1/73 424.5062 IBM Test -1.0371386 2437 2437 2437
## 2440 4/1/73 423.7250 IBM Test -1.2322230 2440 2440 2440
## 2432 8/1/72 413.7174 IBM Test 0.9813313 2432 2432 2432
## Date.POSIX Date.year.fctr Date.month.fctr Date.date.fctr
## 2438 1973-02-01 1973 02 (0.9998,1.0002]
## 2439 1973-03-01 1973 03 (0.9998,1.0002]
## 2437 1973-01-01 1973 01 (0.9998,1.0002]
## 2440 1973-04-01 1973 04 (0.9998,1.0002]
## 2432 1972-08-01 1972 08 (0.9998,1.0002]
## Date.juliandate Date.wkday.fctr Date.wkend Date.hlday Date.hour.fctr
## 2438 32 4 0 0 0
## 2439 60 4 0 0 0
## 2437 1 1 0 0 0
## 2440 91 0 1 0 0
## 2432 214 2 0 0 0
## Date.minute.fctr Date.second.fctr Date.day.minutes Date.zoo
## 2438 0 0 0 631170000
## 2439 0 0 0 631170000
## 2437 0 0 0 631170000
## 2440 0 0 0 631170000
## 2432 0 0 0 631170000
## Date.last2.log1p Date.last4.log1p Date.last8.log1p Date.last16.log1p
## 2438 0 0 14.80073 15.49388
## 2439 0 0 14.69895 15.44428
## 2437 0 0 14.80073 15.47762
## 2440 0 0 14.80073 15.44428
## 2432 0 0 14.80073 15.47762
## Date.last32.log1p .inp.fctr StockPrice.All.X..rcv.glmnet
## 2438 15.88853 IBM 25.20100
## 2439 15.86655 IBM 26.61903
## 2437 15.88898 IBM 22.68959
## 2440 15.86655 IBM 25.18468
## 2432 15.88853 IBM 22.33729
## StockPrice.All.X..rcv.glmnet.err StockPrice.All.X..rcv.glmnet.err.abs
## 2438 413.7006 413.7006
## 2439 410.7851 410.7851
## 2437 401.8166 401.8166
## 2440 398.5403 398.5403
## 2432 391.3801 391.3801
## StockPrice.All.X..rcv.glmnet.is.acc .label
## 2438 FALSE 2438
## 2439 FALSE 2439
## 2437 FALSE 2437
## 2440 FALSE 2440
## 2432 FALSE 2432
if (!is.null(glbFeatsCategory)) {
glbLvlCategory <- merge(glbLvlCategory,
myget_category_stats(obs_df = glbObsFit, mdl_id = glb_sel_mdl_id,
label = "fit"),
by = glbFeatsCategory, all = TRUE)
row.names(glbLvlCategory) <- glbLvlCategory[, glbFeatsCategory]
glbLvlCategory <- merge(glbLvlCategory,
myget_category_stats(obs_df = glbObsOOB, mdl_id = glb_sel_mdl_id,
label="OOB"),
#by=glbFeatsCategory, all=TRUE) glb_ctgry-df already contains .n.OOB ?
all = TRUE)
row.names(glbLvlCategory) <- glbLvlCategory[, glbFeatsCategory]
if (any(grepl("OOB", glbMdlMetricsEval)))
print(orderBy(~-err.abs.OOB.mean, glbLvlCategory)) else
print(orderBy(~-err.abs.fit.mean, glbLvlCategory))
print(colSums(glbLvlCategory[, -grep(glbFeatsCategory, names(glbLvlCategory))]))
}## .inp .n.OOB .n.Fit .n.Tst .freqRatio.Fit .freqRatio.OOB .freqRatio.Tst
## IBM IBM 480 480 480 0.2 0.2 0.2
## BG BG 480 480 480 0.2 0.2 0.2
## CC CC 480 480 480 0.2 0.2 0.2
## PG PG 480 480 480 0.2 0.2 0.2
## GE GE 480 480 480 0.2 0.2 0.2
## err.abs.fit.sum err.abs.fit.mean .n.fit err.abs.OOB.sum
## IBM 29340.236 61.12549 480 66716.72
## BG 10452.639 21.77633 480 64174.95
## CC 8013.138 16.69404 480 40085.31
## PG 7099.550 14.79073 480 39804.47
## GE 8784.733 18.30153 480 32424.37
## err.abs.OOB.mean
## IBM 138.99317
## BG 133.69781
## CC 83.51107
## PG 82.92599
## GE 67.55078
## .n.OOB .n.Fit .n.Tst .freqRatio.Fit
## 2400.0000 2400.0000 2400.0000 1.0000
## .freqRatio.OOB .freqRatio.Tst err.abs.fit.sum err.abs.fit.mean
## 1.0000 1.0000 63690.2954 132.6881
## .n.fit err.abs.OOB.sum err.abs.OOB.mean
## 2400.0000 243205.8281 506.6788write.csv(glbObsOOB[, c(glbFeatsId,
grep(glb_rsp_var, names(glbObsOOB), fixed=TRUE, value=TRUE))],
paste0(gsub(".", "_", paste0(glbOut$pfx, glb_sel_mdl_id), fixed=TRUE),
"_OOBobs.csv"), row.names=FALSE)
fit.models_2_chunk_df <-
myadd_chunk(NULL, "fit.models_2_bgn", label.minor = "teardown")## label step_major step_minor label_minor bgn end elapsed
## 1 fit.models_2_bgn 1 0 teardown 154.723 NA NAglb_chunks_df <- myadd_chunk(glb_chunks_df, "fit.models", major.inc=FALSE)## label step_major step_minor label_minor bgn end elapsed
## 18 fit.models 8 2 2 143.456 154.733 11.277
## 19 fit.models 8 3 3 154.733 NA NA# if (sum(is.na(glbObsAll$D.P.http)) > 0)
# stop("fit.models_3: Why is this happening ?")
#stop(here"); glb2Sav()
sync_glb_obs_df <- function() {
# Merge or cbind ?
for (col in setdiff(names(glbObsFit), names(glbObsTrn)))
glbObsTrn[glbObsTrn$.lcn == "Fit", col] <<- glbObsFit[, col]
for (col in setdiff(names(glbObsFit), names(glbObsAll)))
glbObsAll[glbObsAll$.lcn == "Fit", col] <<- glbObsFit[, col]
if (all(is.na(glbObsNew[, glb_rsp_var])))
for (col in setdiff(names(glbObsOOB), names(glbObsTrn)))
glbObsTrn[glbObsTrn$.lcn == "OOB", col] <<- glbObsOOB[, col]
for (col in setdiff(names(glbObsOOB), names(glbObsAll)))
glbObsAll[glbObsAll$.lcn == "OOB", col] <<- glbObsOOB[, col]
}
sync_glb_obs_df()
print(setdiff(names(glbObsNew), names(glbObsAll)))## character(0)replay.petrisim(pn=glb_analytics_pn,
replay.trans=(glb_analytics_avl_objs <- c(glb_analytics_avl_objs,
"model.selected")), flip_coord=TRUE)## time trans "bgn " "fit.data.training.all " "predict.data.new " "end "
## 0.0000 multiple enabled transitions: data.training.all data.new model.selected firing: data.training.all
## 1.0000 1 2 1 0 0
## 1.0000 multiple enabled transitions: data.training.all data.new model.selected model.final data.training.all.prediction firing: data.new
## 2.0000 2 1 1 1 0
## 2.0000 multiple enabled transitions: data.training.all data.new model.selected model.final data.training.all.prediction data.new.prediction firing: model.selected
## 3.0000 3 0 2 1 0
glb_chunks_df <- myadd_chunk(glb_chunks_df, "fit.data.training", major.inc = TRUE)## label step_major step_minor label_minor bgn end
## 19 fit.models 8 3 3 154.733 161.69
## 20 fit.data.training 9 0 0 161.690 NA
## elapsed
## 19 6.957
## 20 NAStep 9.0: fit data training
#load(paste0(glb_inp_pfx, "dsk.RData"))
if (!is.null(glb_fin_mdl_id) && (glb_fin_mdl_id %in% names(glb_models_lst))) {
warning("Final model same as user selected model")
glb_fin_mdl <- glb_models_lst[[glb_fin_mdl_id]]
} else
# if (nrow(glbObsFit) + length(glbObsFitOutliers) == nrow(glbObsTrn))
if (!all(is.na(glbObsNew[, glb_rsp_var])))
{
warning("Final model same as glb_sel_mdl_id")
glb_fin_mdl_id <- paste0("Final.", glb_sel_mdl_id)
glb_fin_mdl <- glb_sel_mdl
glb_models_lst[[glb_fin_mdl_id]] <- glb_fin_mdl
} else {
if (grepl("RFE\\.X", names(glbMdlFamilies))) {
indepVar <- mygetIndepVar(glb_feats_df)
rfe_trn_results <-
myrun_rfe(glbObsTrn, indepVar, glbRFESizes[["Final"]])
if (!isTRUE(all.equal(sort(predictors(rfe_trn_results)),
sort(predictors(rfe_fit_results))))) {
print("Diffs predictors(rfe_trn_results) vs. predictors(rfe_fit_results):")
print(setdiff(predictors(rfe_trn_results), predictors(rfe_fit_results)))
print("Diffs predictors(rfe_fit_results) vs. predictors(rfe_trn_results):")
print(setdiff(predictors(rfe_fit_results), predictors(rfe_trn_results)))
}
}
# }
if (grepl("Ensemble", glb_sel_mdl_id)) {
# Find which models are relevant
mdlimp_df <- subset(myget_feats_importance(glb_sel_mdl), imp > 5)
# Fit selected models on glbObsTrn
for (mdl_id in gsub(".prob", "",
gsub(mygetPredictIds(glb_rsp_var)$value, "", row.names(mdlimp_df), fixed = TRUE),
fixed = TRUE)) {
mdl_id_components <- unlist(strsplit(mdl_id, "[.]"))
mdlIdPfx <- paste0(c(head(mdl_id_components, -1), "Train"),
collapse = ".")
if (grepl("RFE\\.X\\.", mdlIdPfx))
mdlIndepVars <- myadjustInteractionFeats(glb_feats_df, myextract_actual_feats(
predictors(rfe_trn_results))) else
mdlIndepVars <- trim(unlist(
strsplit(glb_models_df[glb_models_df$id == mdl_id, "feats"], "[,]")))
ret_lst <-
myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = mdlIdPfx,
type = glb_model_type, tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds,
trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = tail(mdl_id_components, 1))),
indepVar = mdlIndepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsTrn, OOB_df = NULL)
glbObsTrn <- glb_get_predictions(df = glbObsTrn,
mdl_id = tail(glb_models_df$id, 1),
rsp_var = glb_rsp_var,
prob_threshold_def =
subset(glb_models_df, id == mdl_id)$opt.prob.threshold.OOB)
glbObsNew <- glb_get_predictions(df = glbObsNew,
mdl_id = tail(glb_models_df$id, 1),
rsp_var = glb_rsp_var,
prob_threshold_def =
subset(glb_models_df, id == mdl_id)$opt.prob.threshold.OOB)
}
}
# "Final" model
if ((model_method <- glb_sel_mdl$method) == "custom")
# get actual method from the mdl_id
model_method <- tail(unlist(strsplit(glb_sel_mdl_id, "[.]")), 1)
if (grepl("Ensemble", glb_sel_mdl_id)) {
# Find which models are relevant
mdlimp_df <- subset(myget_feats_importance(glb_sel_mdl), imp > 5)
if (glb_is_classification && glb_is_binomial)
indepVar <- gsub("(.*)\\.(.*)\\.prob", "\\1\\.Train\\.\\2\\.prob",
row.names(mdlimp_df)) else
indepVar <- gsub("(.*)\\.(.*)", "\\1\\.Train\\.\\2",
row.names(mdlimp_df))
} else
if (grepl("RFE.X", glb_sel_mdl_id, fixed = TRUE)) {
indepVar <- myextract_actual_feats(predictors(rfe_trn_results))
} else indepVar <-
trim(unlist(strsplit(glb_models_df[glb_models_df$id ==
glb_sel_mdl_id
, "feats"], "[,]")))
if (!is.null(glb_preproc_methods) &&
((match_pos <- regexpr(gsub(".", "\\.",
paste(glb_preproc_methods, collapse = "|"),
fixed = TRUE), glb_sel_mdl_id)) != -1))
ths_preProcess <- str_sub(glb_sel_mdl_id, match_pos,
match_pos + attr(match_pos, "match.length") - 1) else
ths_preProcess <- NULL
mdl_id_pfx <- ifelse(grepl("Ensemble", glb_sel_mdl_id),
"Final.Ensemble", "Final")
trnobs_df <- glbObsTrn
if (!is.null(glbObsTrnOutliers[[mdl_id_pfx]])) {
trnobs_df <- glbObsTrn[!(glbObsTrn[, glbFeatsId] %in% glbObsTrnOutliers[[mdl_id_pfx]]), ]
print(sprintf("Outliers removed: %d", nrow(glbObsTrn) - nrow(trnobs_df)))
print(setdiff(glbObsTrn[, glbFeatsId], trnobs_df[, glbFeatsId]))
}
# Force fitting of Final.glm to identify outliers
method_vctr <- unique(c(myparseMdlId(glb_sel_mdl_id)$alg, glbMdlFamilies[["Final"]]))
for (method in method_vctr) {
#source("caret_nominalTrainWorkflow.R")
# glmnet requires at least 2 indep vars
if ((length(indepVar) == 1) && (method %in% "glmnet"))
next
ret_lst <-
myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = mdl_id_pfx,
type = glb_model_type, trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds,
trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = method,
train.preProcess = ths_preProcess)),
indepVar = indepVar, rsp_var = glb_rsp_var,
fit_df = trnobs_df, OOB_df = NULL)
if ((length(method_vctr) == 1) || (method != "glm")) {
glb_fin_mdl <- glb_models_lst[[length(glb_models_lst)]]
glb_fin_mdl_id <- glb_models_df[length(glb_models_lst), "id"]
}
}
}## Warning: Final model same as glb_sel_mdl_idrm(ret_lst)## Warning in rm(ret_lst): object 'ret_lst' not foundglb_chunks_df <- myadd_chunk(glb_chunks_df, "fit.data.training", major.inc=FALSE)## label step_major step_minor label_minor bgn end
## 20 fit.data.training 9 0 0 161.690 162.136
## 21 fit.data.training 9 1 1 162.137 NA
## elapsed
## 20 0.446
## 21 NA#stop(here"); glb2Sav()
if (glb_is_classification && glb_is_binomial)
prob_threshold <- glb_models_df[glb_models_df$id == glb_sel_mdl_id,
"opt.prob.threshold.OOB"] else
prob_threshold <- NULL
if (grepl("Ensemble", glb_fin_mdl_id)) {
# Get predictions for each model in ensemble; Outliers that have been moved to OOB might not have been predicted yet
mdlEnsembleComps <- unlist(str_split(subset(glb_models_df,
id == glb_fin_mdl_id)$feats, ","))
if (glb_is_classification && glb_is_binomial)
mdlEnsembleComps <- gsub("\\.prob$", "", mdlEnsembleComps)
mdlEnsembleComps <- gsub(paste0("^",
gsub(".", "\\.", mygetPredictIds(glb_rsp_var)$value, fixed = TRUE)),
"", mdlEnsembleComps)
for (mdl_id in mdlEnsembleComps) {
glbObsTrn <- glb_get_predictions(df = glbObsTrn, mdl_id = mdl_id,
rsp_var = glb_rsp_var,
prob_threshold_def = prob_threshold)
glbObsNew <- glb_get_predictions(df = glbObsNew, mdl_id = mdl_id,
rsp_var = glb_rsp_var,
prob_threshold_def = prob_threshold)
}
}
glbObsTrn <- glb_get_predictions(df = glbObsTrn, mdl_id = glb_fin_mdl_id,
rsp_var = glb_rsp_var,
prob_threshold_def = prob_threshold)
glb_featsimp_df <- myget_feats_importance(mdl=glb_fin_mdl,
featsimp_df=glb_featsimp_df)
#glb_featsimp_df[, paste0(glb_fin_mdl_id, ".imp")] <- glb_featsimp_df$imp
print(glb_featsimp_df)## All.X..rcv.glmnet.imp imp
## Date.last16.log1p 1.000000e+02 1.000000e+02
## .inp.fctrGE 4.273554e+01 4.273554e+01
## .inp.fctrCC 2.207520e+01 2.207520e+01
## Date.last4.log1p 3.305309e+00 3.305309e+00
## Date.month.fctr02 2.980765e+00 2.980765e+00
## Date.month.fctr05 1.683599e+00 1.683599e+00
## Date.month.fctr10 1.117788e+00 1.117788e+00
## Date.wkday.fctr4 1.064609e+00 1.064609e+00
## Date.month.fctr07 1.046650e+00 1.046650e+00
## Date.last2.log1p 1.011407e+00 1.011407e+00
## Date.month.fctr03 6.733998e-01 6.733998e-01
## Date.month.fctr12 6.599563e-01 6.599563e-01
## Date.month.fctr06 6.219835e-01 6.219835e-01
## .rnorm 4.973828e-01 4.973828e-01
## Date.month.fctr08 4.330194e-01 4.330194e-01
## Date.wkday.fctr6 3.198537e-01 3.198537e-01
## .pos 7.095269e-02 7.095269e-02
## .rownames 1.200204e-02 1.200204e-02
## Date.juliandate 6.236232e-03 6.236232e-03
## .inp.fctrIBM 0.000000e+00 0.000000e+00
## .inp.fctrPG 0.000000e+00 0.000000e+00
## .pos.y 0.000000e+00 0.000000e+00
## Date.last32.log1p 0.000000e+00 0.000000e+00
## Date.last8.log1p 0.000000e+00 0.000000e+00
## Date.month.fctr04 0.000000e+00 0.000000e+00
## Date.month.fctr09 0.000000e+00 0.000000e+00
## Date.month.fctr11 0.000000e+00 0.000000e+00
## Date.wkday.fctr1 0.000000e+00 0.000000e+00
## Date.wkday.fctr2 0.000000e+00 0.000000e+00
## Date.wkday.fctr3 0.000000e+00 0.000000e+00
## Date.wkday.fctr5 0.000000e+00 0.000000e+00
## Date.wkend 0.000000e+00 0.000000e+00if (glb_is_classification && glb_is_binomial)
glb_analytics_diag_plots(obs_df=glbObsTrn, mdl_id=glb_fin_mdl_id,
prob_threshold=glb_models_df[glb_models_df$id == glb_sel_mdl_id,
"opt.prob.threshold.OOB"]) else
glb_analytics_diag_plots(obs_df=glbObsTrn, mdl_id=glb_fin_mdl_id) ## Warning in glb_analytics_diag_plots(obs_df = glbObsTrn, mdl_id =
## glb_fin_mdl_id): Limiting important feature scatter plots to 5 out of 14
## Date StockPrice .inp .src .rnorm .pos .pos.y .rownames
## 38 2/1/73 438.9016 IBM Train -1.75677234 38 38 38
## 39 3/1/73 437.4041 IBM Train -0.38434913 39 39 39
## 37 1/1/73 424.5062 IBM Train 0.41352017 37 37 37
## 40 4/1/73 423.7250 IBM Train 0.03167139 40 40 40
## 32 8/1/72 413.7174 IBM Train -1.66333330 32 32 32
## Date.POSIX Date.year.fctr Date.month.fctr Date.juliandate
## 38 1973-02-01 1973 02 32
## 39 1973-03-01 1973 03 60
## 37 1973-01-01 1973 01 1
## 40 1973-04-01 1973 04 91
## 32 1972-08-01 1972 08 214
## Date.wkday.fctr Date.wkend Date.zoo Date.last2.log1p Date.last4.log1p
## 38 4 0 18000 14.80073 14.80073
## 39 4 0 18000 14.69895 14.69895
## 37 1 0 18000 14.80073 14.80073
## 40 0 1 18000 14.80073 14.80073
## 32 2 0 18000 14.80073 14.80073
## Date.last8.log1p Date.last16.log1p Date.last32.log1p .inp.fctr .lcn
## 38 14.80073 15.49388 16.17927 IBM Fit
## 39 14.69895 15.44428 16.15423 IBM Fit
## 37 14.80073 15.47762 16.17111 IBM Fit
## 40 14.80073 15.44428 16.16253 IBM Fit
## 32 14.80073 15.47762 16.17042 IBM Fit
## Date.date.fctr Date.hlday Date.hour.fctr Date.minute.fctr
## 38 (0.9998,1.0002] 0 0 0
## 39 (0.9998,1.0002] 0 0 0
## 37 (0.9998,1.0002] 0 0 0
## 40 (0.9998,1.0002] 0 0 0
## 32 (0.9998,1.0002] 0 0 0
## Date.second.fctr Date.day.minutes StockPrice.All.X..rcv.glmnet
## 38 0 0 163.5490
## 39 0 0 165.7803
## 37 0 0 162.4554
## 40 0 0 164.8549
## 32 0 0 160.0085
## StockPrice.All.X..rcv.glmnet.err StockPrice.All.X..rcv.glmnet.err.abs
## 38 -275.3526 275.3526
## 39 -271.6238 271.6238
## 37 -262.0508 262.0508
## 40 -258.8701 258.8701
## 32 -253.7089 253.7089
## StockPrice.All.X..rcv.glmnet.is.acc StockPrice.Final.All.X..rcv.glmnet
## 38 FALSE 163.5490
## 39 FALSE 165.7803
## 37 FALSE 162.4554
## 40 FALSE 164.8549
## 32 FALSE 160.0085
## StockPrice.Final.All.X..rcv.glmnet.err
## 38 275.3526
## 39 271.6238
## 37 262.0508
## 40 258.8701
## 32 253.7089
## StockPrice.Final.All.X..rcv.glmnet.err.abs
## 38 275.3526
## 39 271.6238
## 37 262.0508
## 40 258.8701
## 32 253.7089
## StockPrice.Final.All.X..rcv.glmnet.is.acc .label
## 38 FALSE 38
## 39 FALSE 39
## 37 FALSE 37
## 40 FALSE 40
## 32 FALSE 32
dsp_feats_vctr <- c(NULL)
for(var in grep(".imp", names(glb_feats_df), fixed=TRUE, value=TRUE))
dsp_feats_vctr <- union(dsp_feats_vctr,
glb_feats_df[!is.na(glb_feats_df[, var]), "id"])
# print(glbObsTrn[glbObsTrn$UniqueID %in% FN_OOB_ids,
# grep(glb_rsp_var, names(glbObsTrn), value=TRUE)])
print(setdiff(names(glbObsTrn), names(glbObsAll)))## [1] "StockPrice.Final.All.X..rcv.glmnet"
## [2] "StockPrice.Final.All.X..rcv.glmnet.err"
## [3] "StockPrice.Final.All.X..rcv.glmnet.err.abs"
## [4] "StockPrice.Final.All.X..rcv.glmnet.is.acc"for (col in setdiff(names(glbObsTrn), names(glbObsAll)))
# Merge or cbind ?
glbObsAll[glbObsAll$.src == "Train", col] <- glbObsTrn[, col]
print(setdiff(names(glbObsFit), names(glbObsAll)))## character(0)print(setdiff(names(glbObsOOB), names(glbObsAll)))## character(0)for (col in setdiff(names(glbObsOOB), names(glbObsAll)))
# Merge or cbind ?
glbObsAll[glbObsAll$.lcn == "OOB", col] <- glbObsOOB[, col]
print(setdiff(names(glbObsNew), names(glbObsAll)))## character(0)#glb2Sav(); all.equal(savObsAll, glbObsAll); all.equal(sav_models_lst, glb_models_lst)
#load(file = paste0(glbOut$pfx, "dsk_knitr.RData"))
#cmpCols <- names(glbObsAll)[!grepl("\\.Final\\.", names(glbObsAll))]; all.equal(savObsAll[, cmpCols], glbObsAll[, cmpCols]); all.equal(savObsAll[, "H.P.http"], glbObsAll[, "H.P.http"]);
replay.petrisim(pn = glb_analytics_pn,
replay.trans = (glb_analytics_avl_objs <- c(glb_analytics_avl_objs,
"data.training.all.prediction","model.final")), flip_coord = TRUE)## time trans "bgn " "fit.data.training.all " "predict.data.new " "end "
## 0.0000 multiple enabled transitions: data.training.all data.new model.selected firing: data.training.all
## 1.0000 1 2 1 0 0
## 1.0000 multiple enabled transitions: data.training.all data.new model.selected model.final data.training.all.prediction firing: data.new
## 2.0000 2 1 1 1 0
## 2.0000 multiple enabled transitions: data.training.all data.new model.selected model.final data.training.all.prediction data.new.prediction firing: model.selected
## 3.0000 3 0 2 1 0
## 3.0000 multiple enabled transitions: model.final data.training.all.prediction data.new.prediction firing: data.training.all.prediction
## 4.0000 5 0 1 1 1
## 4.0000 multiple enabled transitions: model.final data.training.all.prediction data.new.prediction firing: model.final
## 5.0000 4 0 0 2 1
glb_chunks_df <- myadd_chunk(glb_chunks_df, "predict.data.new", major.inc = TRUE)## label step_major step_minor label_minor bgn end
## 21 fit.data.training 9 1 1 162.137 169.958
## 22 predict.data.new 10 0 0 169.959 NA
## elapsed
## 21 7.821
## 22 NAStep 10.0: predict data new
## Warning in glb_analytics_diag_plots(obs_df = glbObsNew, mdl_id =
## glb_fin_mdl_id, : Limiting important feature scatter plots to 5 out of 14
## Date StockPrice .inp .src .rnorm .pos .pos.y .rownames
## 2438 2/1/73 438.9016 IBM Test -0.4353803 2438 2438 2438
## 2439 3/1/73 437.4041 IBM Test 0.2302633 2439 2439 2439
## 2437 1/1/73 424.5062 IBM Test -1.0371386 2437 2437 2437
## 2440 4/1/73 423.7250 IBM Test -1.2322230 2440 2440 2440
## 2432 8/1/72 413.7174 IBM Test 0.9813313 2432 2432 2432
## Date.POSIX Date.year.fctr Date.month.fctr Date.juliandate
## 2438 1973-02-01 1973 02 32
## 2439 1973-03-01 1973 03 60
## 2437 1973-01-01 1973 01 1
## 2440 1973-04-01 1973 04 91
## 2432 1972-08-01 1972 08 214
## Date.wkday.fctr Date.wkend Date.zoo Date.last2.log1p
## 2438 4 0 631170000 0
## 2439 4 0 631170000 0
## 2437 1 0 631170000 0
## 2440 0 1 631170000 0
## 2432 2 0 631170000 0
## Date.last4.log1p Date.last8.log1p Date.last16.log1p Date.last32.log1p
## 2438 0 14.80073 15.49388 15.88853
## 2439 0 14.69895 15.44428 15.86655
## 2437 0 14.80073 15.47762 15.88898
## 2440 0 14.80073 15.44428 15.86655
## 2432 0 14.80073 15.47762 15.88853
## .inp.fctr .lcn StockPrice.Final.All.X..rcv.glmnet
## 2438 IBM OOB 25.20100
## 2439 IBM OOB 26.61903
## 2437 IBM OOB 22.68959
## 2440 IBM OOB 25.18468
## 2432 IBM OOB 22.33729
## StockPrice.Final.All.X..rcv.glmnet.err
## 2438 413.7006
## 2439 410.7851
## 2437 401.8166
## 2440 398.5403
## 2432 391.3801
## StockPrice.Final.All.X..rcv.glmnet.err.abs
## 2438 413.7006
## 2439 410.7851
## 2437 401.8166
## 2440 398.5403
## 2432 391.3801
## StockPrice.Final.All.X..rcv.glmnet.is.acc .label
## 2438 FALSE 2438
## 2439 FALSE 2439
## 2437 FALSE 2437
## 2440 FALSE 2440
## 2432 FALSE 2432
## [1] TRUE## [1] "glb_sel_mdl_id: All.X##rcv#glmnet"## [1] "glb_fin_mdl_id: Final.All.X##rcv#glmnet"## [1] "Cross Validation issues:"
## Max.cor.Y.rcv.1X1###glmnet
## 0## min.RMSE.OOB max.R.sq.OOB max.Adj.R.sq.fit
## Max.cor.Y##rcv#rpart 63.08067 -0.2678863 NA
## Low.cor.X##rcv#glmnet 113.42926 -3.0995666 0.4385103
## All.X##rcv#glmnet 113.42926 -3.0995666 0.4385103
## Max.cor.Y.rcv.1X1###glmnet 146.85585 -5.8717963 0.4342670
## Max.cor.Y.Time.Lag##rcv#glmnet 232.34139 -16.2004933 0.4433471
## Interact.High.cor.Y##rcv#glmnet 381.82413 -45.4530763 0.6138542
## All.X##rcv#glm 771.99279 -188.8953069 0.4417231
## min.RMSE.fit
## Max.cor.Y##rcv#rpart 24.29990
## Low.cor.X##rcv#glmnet 42.07752
## All.X##rcv#glmnet 42.07752
## Max.cor.Y.rcv.1X1###glmnet 42.09290
## Max.cor.Y.Time.Lag##rcv#glmnet 41.81473
## Interact.High.cor.Y##rcv#glmnet 34.88221
## All.X##rcv#glm 42.20301## [1] "All.X##rcv#glmnet OOB RMSE: 113.4293"## err.abs.fit.sum err.abs.OOB.sum err.abs.trn.sum err.abs.new.sum
## IBM 29340.236 66716.72 29340.236 66716.72
## BG 10452.639 64174.95 10452.639 64174.95
## CC 8013.138 40085.31 8013.138 40085.31
## PG 7099.550 39804.47 7099.550 39804.47
## GE 8784.733 32424.37 8784.733 32424.37
## .freqRatio.Fit .freqRatio.OOB .freqRatio.Tst .n.Fit .n.OOB .n.Tst
## IBM 0.2 0.2 0.2 480 480 480
## BG 0.2 0.2 0.2 480 480 480
## CC 0.2 0.2 0.2 480 480 480
## PG 0.2 0.2 0.2 480 480 480
## GE 0.2 0.2 0.2 480 480 480
## .n.fit .n.new .n.trn err.abs.OOB.mean err.abs.fit.mean
## IBM 480 480 480 138.99317 61.12549
## BG 480 480 480 133.69781 21.77633
## CC 480 480 480 83.51107 16.69404
## PG 480 480 480 82.92599 14.79073
## GE 480 480 480 67.55078 18.30153
## err.abs.new.mean err.abs.trn.mean
## IBM 138.99317 61.12549
## BG 133.69781 21.77633
## CC 83.51107 16.69404
## PG 82.92599 14.79073
## GE 67.55078 18.30153
## err.abs.fit.sum err.abs.OOB.sum err.abs.trn.sum err.abs.new.sum
## 63690.2954 243205.8281 63690.2954 243205.8281
## .freqRatio.Fit .freqRatio.OOB .freqRatio.Tst .n.Fit
## 1.0000 1.0000 1.0000 2400.0000
## .n.OOB .n.Tst .n.fit .n.new
## 2400.0000 2400.0000 2400.0000 2400.0000
## .n.trn err.abs.OOB.mean err.abs.fit.mean err.abs.new.mean
## 2400.0000 506.6788 132.6881 506.6788
## err.abs.trn.mean
## 132.6881## [1] "Final.All.X##rcv#glmnet prediction stats for glbObsNew:"
## id max.R.sq.new min.RMSE.new max.Adj.R.sq.new
## 1 All.X##rcv#glmnet -3.099567 113.4293 -3.15499## [1] "Features Importance for selected models:"## All.X..rcv.glmnet.imp
## Date.last16.log1p 100.00000
## .inp.fctrGE 42.73554
## .inp.fctrCC 22.07520## [1] "glbObsNew prediction stats:"## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## label step_major step_minor label_minor bgn end
## 22 predict.data.new 10 0 0 169.959 188.543
## 23 display.session.info 11 0 0 188.544 NA
## elapsed
## 22 18.584
## 23 NANull Hypothesis (\(\sf{H_{0}}\)): mpg is not impacted by am_fctr.
The variance by am_fctr appears to be independent. #{r q1, cache=FALSE} # print(t.test(subset(cars_df, am_fctr == "automatic")$mpg, # subset(cars_df, am_fctr == "manual")$mpg, # var.equal=FALSE)$conf) # We reject the null hypothesis i.e. we have evidence to conclude that am_fctr impacts mpg (95% confidence). Manual transmission is better for miles per gallon versus automatic transmission.
## label step_major step_minor label_minor bgn
## 2 inspect.data 2 0 0 8.854
## 6 extract.features.datetime 3 1 1 76.288
## 3 scrub.data 2 1 1 48.691
## 22 predict.data.new 10 0 0 169.959
## 16 fit.models 8 0 0 117.848
## 18 fit.models 8 2 2 143.456
## 17 fit.models 8 1 1 134.981
## 21 fit.data.training 9 1 1 162.137
## 19 fit.models 8 3 3 154.733
## 7 extract.features.image 3 2 2 110.590
## 1 import.data 1 0 0 6.273
## 15 select.features 7 0 0 115.812
## 11 extract.features.end 3 6 6 114.247
## 20 fit.data.training 9 0 0 161.690
## 12 manage.missing.data 4 0 0 115.160
## 14 partition.data.training 6 0 0 115.529
## 10 extract.features.string 3 5 5 114.187
## 9 extract.features.text 3 4 4 114.133
## 13 cluster.data 5 0 0 115.476
## 4 transform.data 2 2 2 76.226
## 8 extract.features.price 3 3 3 114.094
## 5 extract.features 3 0 0 76.267
## end elapsed duration
## 2 48.690 39.836 39.836
## 6 110.590 34.302 34.302
## 3 76.225 27.534 27.534
## 22 188.543 18.584 18.584
## 16 134.981 17.133 17.133
## 18 154.733 11.277 11.277
## 17 143.455 8.474 8.474
## 21 169.958 7.821 7.821
## 19 161.690 6.957 6.957
## 7 114.094 3.504 3.504
## 1 8.854 2.581 2.581
## 15 117.848 2.036 2.036
## 11 115.160 0.913 0.913
## 20 162.136 0.446 0.446
## 12 115.476 0.316 0.316
## 14 115.811 0.282 0.282
## 10 114.247 0.060 0.060
## 9 114.186 0.053 0.053
## 13 115.529 0.053 0.053
## 4 76.267 0.041 0.041
## 8 114.132 0.039 0.038
## 5 76.288 0.021 0.021
## [1] "Total Elapsed Time: 188.543 secs"